@comment{List of conferences: ACII2013 => Affective BCI Workshop, International Conference on Affective Computing and Intelligent Interaction, Geneva, Switzerland ACL 2013 => The 51st Annual Meeting of the Association for Computational Linguistics, Sofia, Bulgaria AMTA 2008 => Eighth Conference of the Association for Machine Translation in the Americas, Waikiki, Hawai'i Biodevices 2019 => 12th International Conference on Biomedical Electronics and Devices Biosignals 2008 => 1st International Conference on Bio-inspired Systems and Signal Processing, Madeira, Portugal Biosignals 2009 => 2nd International Conference on Bio-inspired Systems and Signal Processing, Porto, Portugal BIOSIGNALS 2012 => 5th International Conference on Bio-inspired Systems and Signal Processing BIOSIGNALS 2013 => 6th International Conference on Bio-inspired Systems and Signal Processing BIOSIGNALS 2014 => 7th International Conference on Bio-inspired Systems and Signal Processing BIOSIGNALS 2015 => 8th International Conference on Bio-inspired Systems and Signal Processing BIOSIGNALS 2018 => 11th International Conference on Bio-inspired Systems and Signal Processing, Madeira, Portugal BIOSIGNALS 2020 => 13th International Conference on Bio-inspired Systems and Signal Processing BIOSIGNALS 2021 => 14th International Conference on Bio-inspired Systems and Signal Processing BIOSIGNALS 2022 => 15th International Conference on Bio-inspired Systems and Signal Processing BIOSIGNALS 2026 => 19th International Conference on Bio-inspired Systems and Signal Processing HEALTHINF 2022 => 15th International Conference on Health Informatics CHISIG => 23nd conference of the computer-human interaction special interest group of Australia on Computer-human interaction: design (OZCHI 2009), Melbourne, Australia EMBC 2014 => 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society EMBC'12 => International Conference of the IEEE Engineering in Medicine and Biology Society, San Diego, USA EMBC'13 => International Conference of the IEEE Engineering in Medicine and Biology Society, Osaka, Japan International Conference of the IEEE Engineering in Medicine and Biology Society, Osaka, Japan International Conference of the IEEE Engineering in Medicine and Biology Society, Osaka, Japan EUSIPCO 2021 => 29th European Signal Processing Conference IALP => The International Conference on Asian Language Processing, Hanoi, Vietnam ICASSP => IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2012 => 37th International Conference on Acoustics, Speech, and Signal Processing, Kyoto, Japan ICASSP 2013 => The 38th International Conference on Acoustics, Speech, and Signal Processing ICASSP 2014 => International Conference on Acoustics, Speech, and Signal Processing The 39th International Conference on Acoustics, Speech, and Signal Processing ICASSP 2015 => The 40th International Conference on Acoustics, Speech, and Signal Processing, Brisbane, Australia ICMI'14 => 14th ACM International Conference on Multimodal Interaction ICONIP 2012 => 19th International Conference on Neural Information Processing, Doha, Qatar Interspeech 2010 => 11th Annual Conference of the International Speech Communication Association, Makuhari, Japan 11th Annual Conference of the International Speech Communication Association, Makuhari, Japan Interspeech 2012 => 13th Annual Conference of the International Speech Communication Association, Portland, Oregon Interspeech 2013 => 14th Annual Conference of the International Speech Communication Association, Lyon, France Interspeech 2014 => The 15th Annual Conference of the International Speech Communication Association, Singapore The 15th Annual Conference of the International Speech Communication Association, Singapore ISWC '12 => 16th International Symposium on Wearable Computers IUI '12 => International Conference on Intelligent User Interfaces IWSLT 2011 => The International Workshop on Spoken Language Translation, San Francisco, USA JEP => Journies d'E'tude sur la Parole Invited paper and keynote talk LREC 2014 => The 9th edition of the Language Resources and Evaluation Conference, Reykjavik, Iceland MLMI => 4th Joint Workshop on Machine Learning and Multimodal Interaction, Lecture Notes in Computer Science Multimedia Interaction Human Machine Interface => Proceedings of ICME PERCOM 2022 => 20th IEEE International Conference on Pervasive Computing and Communications Side event of Biosignals 2010 conference => First International Workshop on Bio-inspired Human-Machine Interfaces and Healthcare Applications SIGMAP 2022 => 19th International Conference on Signal Processing and Multimedia Applications SLSP 2013 => The 1st International Conference on Statistical Language and Speech Processing SLT 2012 => The Fourth IEEE Workshop on Spoken Language Technology SLTU 2014 => The 4th Workshop on Spoken Language Technologies for Under-resourced Languages, St. Petersburg, Russia SLTU'12 => The third International Workshop on Spoken Languages Technologies for Under-resourced Languages The third International Workshop on Spoken Languages Technologies for Under-resourced Languages, Cape Town, South Africa UbiComp 2013 => 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing und Kommunikationstechnologien in der Sportmotorik, 11. Tagung der dvs-Sektion Sportmotorik => Informations VISAPP 2012 => International Conference on Computer Vision Theory and Applications 2012 } @comment{List of conferences with no shortname: 1. Fachtagung Biophysiologische Interfaces 10th Annual Conference of the International Speech Communication Association 11th Annual Conference of the International Speech Communication Association 14th Annual Conference of the International Speech Communication Association, Lyon, France 155th Meeting of the Acoustical Society of America 15th European Signal Processing Conference 16th International Congress of Phonetic Sciences 18th IEEE International Symposium on Robot and Human Interactive Communication 1999 Proceedings of the International Conference on Speech Processing 19th International Conference on Pattern Recognition 1st International Workshop on Spoken Dialog Systems 2009 International Conference on Affective Computing & Intelligent Interaction 20th International Conference on Pattern Recognition 21st Swedish Phonetics Conference 2nd International Conference on Multi-modal Interfaces 2nd Workshop on Spoken Languages Technologies for Under-resourced Languages 33rd Annual German Conference on Artificial Intelligence 2010 33rd IEEE International Conference on Acoustics, Speech, and Signal Processing 4th Biennial Workshop on DSP for In-Vehicle Systems and Safety 4th International Conference on Applied Human Factors and Ergonomics 4th International Conference on Speech Prosody 5th Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms 6th International Conference on Language Resources and Evaluation 8th IEEE-RAS International Conference on Humanoid Robots, Workshop Imitation and Coaching in Humanoid Robots 9th Annual Conference of the International Speech Communication Association 9th IEEE-RAS International Conference on Humanoid Robots, Workshop Imitation and Coaching in Humanoid Robots 9th SIGdial Workshop on Discourse and Dialogue Adaptation for Speech Processing Systems Affective Computing and Intelligent Interaction 2011, ACII 2011 ARPA Workshop on Speech and Natural Language Technology Automatic Speech Recognition and Understanding Biomechanik - Grundlagenforschung und Anwendung, Tagung der dvs-Sektion Biomechanik Computers, Linguistics, and Phonetics between Language and Speech. Proceedings of the 4th Conference on NLP Conference on Speech and Language Systems for Human Communication Continuous Speech Recognition Systems diverse Workshops 2007 EARS Rich Transcription Workshop Elektronische Sprachsignalverarbeitung ESSV First Augmented Human International Conference French-German Workshop on Humanoid and Legged Robots, HLR 2006 Human Language Technology & North American Chapter of the Association for Computational Linguistics Human Language Technology Conference ICASSP IEEE International Conference on Acoustics, Speech and Signal Processing IEEE Workshop on Spoken Language Technology IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2011 In proceedings of the 19th Swedish Phonetics Conference In proceedings of the 5th ELRA International Conference on Language Resources and Evaluation In proceedings of the 5th Slovenian and 1st International Language Technologies Conference In proceedings of the 8th ISCA/ACL SIGdial Workshop on Discourse and Dialogue In proceedings of the 9th ISCA International Conference on Spoken Language Processing International BCI Meeting 2013, Asilomar, USA International BCI Meeting 2013, Asilomar, USA International Conference of Spoken Language Processing International Conference on Bio-inspired Systems and Signal Processing International Conference on Bio-inspired Systems and Signal Processing 2013 International Conference on Intelligent User Interfaces 2013, Santa Monica, USA International Conference on Multimodal Interaction, ICMI 2011 International Conference on Multimodal Interfaces International Conference on Social Robotics International IEEE EMBS Neural Engineering Conference 2013, San Diego, USA International Workshop on East-Asien Language Resources and Evaluation International Workshop on Spoken Langage Translation Interspeech 2010 Interspeech 2011 Invited keynote talk at the ISCA Tutorial and Research Workshop on Multilingual Speech and Language Processing Invited paper, Special Session on Multilinguality in Speech Processing, Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing Landessymposium Multilingual Information Retrieval Dialogs: 2nd SQEL Workshop Neural Information Processing Systems NIST Meeting Recognition Workshop NIST SRE Workshop 2008 Non-native Speech Nordic Prosody X Panel Session on Automatic Speech Recognition and Understanding Presented at the 3rd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms Proceedings of 2014 APSIPA Annual Summit and Conference Proceedings of ACL Proceedings of International Workshop of Spoken Language Translation Proceedings of Interspeech Proceedings of the 1st Workshop on Text, Speech, and Dialogue, ; TSD Proceedings of the 3rd Conference on Natural Language Processing and Speech Technology Proceedings of the 5th European Conference on Speech Communication and Technology, Vol. 1 Proceedings of the 6th European Conference on Speech Communication and Technology Proceedings of the 7th European Conference on Speech Communication and Technology Proceedings of the 8th European Conference on Speech Communication and Technology Proceedings of the Automatic Speech Recognition and Understanding Workshop Proceedings of the DARPA Broadcast News Transcription and Understanding Proceedings of the Eurospeech Proceedings of the HLT-NAACL 2007 Proceedings of the Human Language Technologies Proceedings of the Human Language Technology Meeting Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol. 1 Proceedings of the International Conference of Spoken Language Processing Proceedings of the International Conference of Spoken Language Processing , Vol. 5 Proceedings of the International Conference on Multimodal Input Proceedings of the International Conference on Multimodal Interfaces Proceedings of the ISCA Tutorial and Researc Workshop on Multilingual Speech and Language Processing Proceedings of the Speech Research Symposium SRS XV Proceedings of the Speech-to-Speech Translation Workshop on the 40th Anniversary Meeting of the Association for Computational Linguistics Proceedings of the Workshop of Automatic Speech Recognition Understanding Proceedings of the Workshop on Hands-Free Speech Communication Proceedings of the Workshop on Multilingual Speech Communication SLTU: Workshop on Spoken Language Technologies for Under-Resourced Languages SPECOM Speech and Computer Sportinformatik trifft Sporttechnologie, Tagung der dvs-Sektion Sportinformatik in Kooperation mit der deutschen interdisziplin Sportinformatik trifft Sporttechnologie, Tagung der dvs-Sektion Sportinformatik in Kooperation mit der Deutschen Interdisziplinären Vereinigung für Sporttechnologie Workshop on Multi-lingual Interoperability in Speech Technology Workshop on Speech and Communication } @mastersthesis{zahner2014konvertierung, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/MA_Zahner_Druckversion_bunt_korrigiert.pdf}, school={Karlsruher Institut für Technologie}, title={Konvertierung von myoelektrischen Signalen der Gesichtsmuskulatur zu Sprache: Ein Unit Selection-Ansatz}, year={2014}, supervisor={Wand, Michael and Janke, Matthias and Schultz, Tanja}, author={Zahner, Marlene}, abstract={In dieser Masterarbeit wird ein neuer Ansatz zur Konvertierung von Muskelsignalen zu hörbarer Sprache vorgestellt. Allein die elektrischen Signale der Gesichtsmuskulatur werden mittels Oberflächenelektroden aufgezeichnet, ohne dass der Sprecher hörbare Laute artikulieren muss. Anschließend werden die Signale in kurze Abschnitte unterteilt und mit bereits aufgezeichneten EMG-Signalen verglichen, die wiederum mit Sprachsegmenten verknüpft sind. Die gewählten Sprachsegmente werden dann erneut zu Sprache zusammengesetzt. Diese Vorgehensweise des Wählens und Zusammensetzens bereits vorhandener Sprachabschnitte wird Unit Selection genannt. Der Vorteil, Muskelsignale in Sprache umzuwandeln liegt darin, dass man auch in lauten Umgebungen oder für einen Sprecher mit Sprachbehinderungen hörbare akustische Signale erzeugen kann, die zu einem bestimmten Empfänger geleitet werden können. Beistehende werden hierbei nicht belästigt und die Privatsphäre wird ebenfalls gewahrt. Frühere Experimente haben die Machbarkeit der Umwandlung myoelektrischer Signale zu Sprache gezeigt, jedoch existieren Probleme vor allem bei der Natürlichkeit der erzeugten Sprache. Durch das hier vorgestellte Verfahren sollen sowohl Verstäandlichkeit als auch Natürlichkeit der konvertierten Sprache gegenüber bereits existierenden Ansätzen verbessert werden. Die Evaluation der konvertierten Sprache zeigt in einer objektiven Evaluationsmethode eine Steigerung von durchschnittlich 13% gegenüber einem bereits existierenden Ansatz. Ein Hörtest zur subjektiven Bewertung der Natürlichkeit bestätigt ebenfalls die Verbesserung der konvertierten Sprache durch den hier vorgestellten Ansatz.} } @mastersthesis{diener2015improving, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/diener2015improving.pdf}, school={Karlsruher Institut für Technologie}, title={Improving Unit Selection based EMG-to-Speech Conversion}, year={2015}, supervisor={Janke, Matthias and Schultz, Tanja}, author={Diener, Lorenz}, abstract={This master’s thesis introduces a new approach to improve the unit-selection based conversion of facial myoelectric signals to audible speech. Surface electromyography is the recording of electric signals generated by muscle activity using surface electrodes attached to the skin. Past work has shown that it is feasible to generate audible speech signals from facial electromyographic activity generated during speech production, using several different approaches. This work focuses on the unit-selection approach to conversion, where the speech signal is reconstructed by concatenating pieces of target audio data selected by a similarity criterion calculated on the parallel sequence of source electromyographic data. A novel approach, based on optimizing the database that units are selected from by using unit clustering to generate more prototypical units and improve the selection process, is introduced and evaluated. In total, we obtain a qualitative improvement of up to 14.92 percent relative over a baseline unit selection system, while improving the time taken for conversion by up to 98%.} } @mastersthesis{hartmann2020feature, school={Universität Bremen}, year={2020}, title={Feature Selection for Multimodal Human Activity Recognition}, supervisor={Liu, Hui and Schultz, Tanja and Shi, Hui}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/MA_Hartmann_2020.pdf}, author={Hartmann, Yale} } @mastersthesis{wang2022thesis, title={Towards Automatic Heart Sound Segmentation}, author={Wang, Wei}, year={2022}, supervisor={Liu, Hui and Ren, Zhao and Peissig, Jürgen and Nejdl, Wolfgang}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/MA_Wang_2022.pdf}, doi={10.13140/RG.2.2.21870.59202}, abstract={The heart sound signal has been studied wildly over the past several decades. The goal of this thesis is to investigate the impact of heart sound segmentation on heart sound classification. Heart sound segmentation, which involves dividing heart sounds into distinct parts, is commonly used as a pre-processing step for heart sound classification, but recent research has demonstrated that heart sound classification can also be effective without segmentation. Automated heart sound segmentation and classification, such as the detection of abnormal heart sounds, have the potential to screen for diseases in various clinical settings. The heart sound database used in this thesis is the dataset from the PhysioNet/CinC Challenge 2022, which is available to the public. To find out, the heart sounds will be segmented by a method of time-series query search with the TSSEARCH toolkit. After that, the segmented heart sounds will be processed by a Convolutional Neural Network (CNN) model for the classification task. To compare performance, the classification results will be compared to those obtained from heart sound classification without segmentation.} } @phdthesis{herff2016speech, school={University of Bremen}, title={Speech Processes for Brain-Computer Interfaces}, year={2016}, supervisor={Schultz, Tanja and Krusienski, Dean J}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Herff2016Diss.pdf}, author={Herff, Christian} } @article{doi:10.1080/2326263X.2016.1275488, author = {Jane E. Huggins and Christoph Guger and Mounia Ziat and Thorsten O. Zander and Denise Taylor and Michael Tangermann and Aureli Soria-Frisch and John Simeral and Reinhold Scherer and Rüdiger Rupp and Giulio Ruffini and Douglas K. R. Robinson and Nick F. Ramsey and Anton Nijholt and Gernot Müller-Putz and Dennis J. McFarland and Donatella Mattia and Brent J. Lance and Pieter-Jan Kindermans and Iñaki Iturrate and Christian Herff and Disha Gupta and An H. Do and Jennifer L. Collinger and Ricardo Chavarriaga and Steven M. Chase and Martin G. Bleichner and Aaron Batista and Charles W. Anderson and Erik J. Aarnoutse}, title = {Workshops of the Sixth International Brain–Computer Interface Meeting: brain–computer interfaces past, present, and future}, journal = {Brain-Computer Interfaces}, volume = {4}, number = {1-2}, pages = {3-36}, year = {2017}, doi = {10.1080/2326263X.2016.1275488}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/bci_workshops.pdf}, eprint = {http://dx.doi.org/10.1080/2326263X.2016.1275488} } @inproceedings{herff2017NAT, title={EVALUATING FNIRS-BASED WORKLOAD DISCRIMINATION IN A REALISTIC DRIVING SCENARIO}, year={2017}, booktitle={The First Biannual Neuroadaptive Technology Conference}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/NAT2017_cherff.pdf}, author={Herff, Christian and Putze, Felix and Schultz, Tanja}, } @inproceedings{herff2017musicBCI, title={Signal Characterization for a Musical Rhythm BCI}, year={2017}, booktitle={Engineering in Medicine and Biology Society (EMBC), 2016 39th Annual International Conference of the IEEE}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Herff2017MusicBCI.pdf}, author={Herff, Steffen A. and Johnson, Garett D. and Milne, Andrew J. and Herff, Christian and Kim, Jee H. and Shih, Jerry J. and Krusienski, Dean J.}, } @Inbook{Herff2017Award, author={Herff, Christian and de Pesters, Adriana and Heger, Dominic and Brunner, Peter and Schalk, Gerwin and Schultz, Tanja}, editor={Guger, Christoph and Allison, Brendan and Ushiba, Junichi}, title={Towards Continuous Speech Recognition for BCI}, bookTitle={Brain-Computer Interface Research: A State-of-the-Art Summary 5}, year={2017}, publisher={Springer International Publishing}, address={Cham}, pages={21--29}, isbn={978-3-319-57132-4}, doi={10.1007/978-3-319-57132-4_3}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Herff2017Award.pdf} } @ARTICLE{Herff2016Review, AUTHOR={Herff, Christian and Schultz, Tanja}, TITLE={Automatic Speech Recognition from Neural Signals: A Focused Review}, JOURNAL={Frontiers in Neuroscience}, VOLUME={10}, PAGES={429}, YEAR={2016}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Herff2016Review.pdf}, DOI={10.3389/fnins.2016.00429}, ISSN={1662-453X}, ABSTRACT={Speech interfaces have become widely accepted and are nowadays integrated in various real-life applications and devices. They have become a part of our daily life. However, speech interfaces presume the ability to produce intelligible speech, which might be impossible due to either loud environments, bothering bystanders or incapabilities to produce speech (i.e.~patients suffering from locked-in syndrome). For these reasons it would be highly desirable to not speak but to simply envision oneself to say words or sentences. Interfaces based on imagined speech would enable fast and natural communication without the need for audible speech and would give a voice to otherwise mute people. This focused review analyzes the potential of different brain imaging techniques to recognize speech from neural signals by applying Automatic Speech Recognition technology. We argue that modalities based on metabolic processes, such as functional Near Infrared Spectroscopy and functional Magnetic Resonance Imaging, are less suited for Automatic Speech Recognition from neural signals due to low temporal resolution but are very useful for the investigation of the underlying neural mechanisms involved in speech processes. In contrast, electrophysiologic activity is fast enough to capture speech processes and is therefor better suited for ASR. Our experimental results indicate the potential of these signals for speech recognition from neural data with a focus on invasively measured brain activity (electrocorticography). As a first example of Automatic Speech Recognition techniques used from neural signals, we discuss the \emph{Brain-to-text} system.} } @INPROCEEDINGS{HerffEMBC2016, author={Herff, C. and Johnson, G. and Diener, L. and Shih, J. and Krusienski, D. and Schultz, T.}, booktitle={Engineering in Medicine and Biology Society (EMBC), 2016 38th Annual International Conference of the IEEE}, title={Towards direct speech synthesis from ECoG: A pilot study}, year={2016}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/HerffEMBC_16.pdf}, poster={http://www.csl.uni-bremen.de/cms/images/documents/publications/Herff_EMBC16_poster.pdf}, month={Aug}, abstract={Most current Brain-Computer Interfaces (BCIs) achieve high information transfer rates using spelling paradigms based on stimulus-evoked potentials. Despite the success of this interfaces, this mode of communication can be cumbersome and unnatural. Direct synthesis of speech from neural activity represents a more natural mode of communi- cation that would enable users to convey verbal messages in real-time. In this pilot study with one participant, we demonstrate that electrocoticography (ECoG) intracranial activity from temporal areas can be used to resynthesize speech in real-time. This is accomplished by reconstructing the audio magnitude spectrogram from neural activity and subsequently creating the audio waveform from these reconstructed spectrograms. We show that significant correlations between the original and reconstructed spectrograms and temporal waveforms can be achieved. While this pilot study uses audibly spoken speech for the models, it represents a first step towards speech synthesis from speech imagery.} } @INPROCEEDINGS{diener2016initial, author={Diener, L. and Herff, C. and Janke, M. and Schultz, T.}, booktitle={Engineering in Medicine and Biology Society (EMBC), 2016 38th Annual International Conference of the IEEE}, title={An Initial Investigation into the Real-Time Conversion of Facial Surface EMG Signals to Audible Speech}, year={2016}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/DienerEMBC_16.pdf}, poster={http://www.csl.uni-bremen.de/cms/images/documents/publications/DienerEMBC_16_poster.pdf}, month={Aug}, abstract={This paper presents early-stage results of our investigations into the direct conversion of facial surface electromyographic (EMG) signals into audible speech in a real-time setting, enabling novel avenues for research and system improvement through real-time feedback. The system uses a pipeline approach to enable online acquisition of EMG data, extraction of EMG features, mapping of EMG features to audio features, synthesis of audio waveforms from audio features and output of the audio waveforms via speakers or headphones. Our system allows for performing EMG-to-Speech conversion with low latency and on a continuous stream of EMG data, enabling near instantaneous audio output during audible as well as silent speech production. In this paper, we present an analysis of our systems components for latency incurred, as well as the trade-offs between conversion quality, latency and training duration required.} } @inproceedings{herff2016music, title={Music rhythm reconstruction from ECoG}, year={2016}, booktitle={International BCI Meeting 2016, Asilomar, USA}, doi={10.3217/978-3-85125-467-9-212}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Herff_BCIMeeting16.pdf}, author={Herff, Christian and Johnson, Garett and Shih, Jerry and Schultz, Tanja and Krusienski, Dean}, } @ARTICLE{10.3389/fnhum.2015.00617, AUTHOR={Von Lühmann, Alexander and Herff, Christian and Heger, Dominic and Schultz, Tanja}, TITLE={Towards a wireless open source instrument:functional Near-Infrared Spectroscopy in mobile neuroergonomics and BCI applications}, JOURNAL={Frontiers in Human Neuroscience}, VOLUME={9}, YEAR={2015}, NUMBER={617}, URL={http://www.frontiersin.org/human_neuroscience/10.3389/fnhum.2015.00617/abstract}, DOI={10.3389/fnhum.2015.00617}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/fnhum-09-00617.pdf}, ISSN={1662-5161}, ABSTRACT={Brain-Computer Interfaces (BCIs) and neuroergonomics research have high requirements regarding robustness and mobility. Additionally, fast applicability and customization are desired. Functional Near-Infrared Spectroscopy (fNIRS) is an increasingly established technology with a potential to satisfy these conditions. EEG acquisition technology, currently one of the main modalities used for mobile brain activity assessment, is widely spread and open for access and thus easily customizable. fNIRS technology on the other hand has either to be bought as a predefined commercial solution or developed from scratch using published literature. To help reducing time and effort of future custom designs for research purposes, we present our approach toward an open source multichannel stand-alone fNIRS instrument for mobile NIRS-based neuroimaging, neuroergonomics and BCI/BMI applications. The instrument is low-cost, miniaturized, wireless and modular and openly documented on www.opennirs.org. It provides features such as scalable channel number, configurable regulated light intensities, programmable gain and lock-in amplification. In this paper, the system concept, hardware, software and mechanical implementation of the lightweight stand-alone instrument are presented and the evaluation and verification results of the instrument's hardware and physiological fNIRS functionality are described. Its capability to measure brain activity is demonstrated by qualitative signal assessments and a quantitative mental arithmetic based BCI study with 12 subjects.}} @inproceedings{heger2015continuous, title={Continuous Speech Recognition from ECoG}, author={Heger, Dominic and Herff, Christian and Pesters, Adriana de and Telaar, Dominic and Brunner, Peter and Schalk, Gerwin and Schultz, Tanja}, booktitle={Sixteenth Annual Conference of the International Speech Communication Association}, year={2015}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/IS2015_brain2text.pdf}, abstract={Continuous speech production is a highly complex process involving many parts of the human brain. To date, no fundamental representation that allows for decoding of continuous speech from neural signals has been presented. Here we show that techniques from automatic speech recognition can be applied to decode a textual representation of spoken words from neural signals. We model phones as the fundamental unit of the speech process in invasively measured brain activity (intracranial electrocorticographic (ECoG)) recordings. These phone models give insights into timings and locations of neural processes associated with the continuous production of speech and can be used in a speech recognizer to decode the neural data into their textual representations. When restricting the dictionary to small subsets, Word Error Rates as low as 25% can be achieved. As the brain activity data sets are fairly small, alternative approaches to Gaussian models are investigated by relying on robust, regularized discriminative models.} } @article{thurer_increased_2015, title = {Increased gamma band power during movement planning coincides with motor memory retrieval}, issn = {1095-9572}, doi = {10.1016/j.neuroimage.2015.10.008}, abstract = {The retrieval of motor memory requires a previous memory encoding and subsequent consolidation of the specific motor memory. Previous work showed that motor memory seems to rely on different memory components (e.g., implicit, explicit). However, it is still unknown if explicit components contribute to the retrieval of motor memories formed by dynamic adaptation tasks and which neural correlates are linked to memory retrieval. We investigated the lower and higher gamma bands of subjects' electroencephalography during encoding and retrieval of a dynamic adaptation task. A total of 24 subjects were randomly assigned to a treatment and control group. Both groups adapted to a force field A on day 1 and were re-exposed to the same force field A on day 3 of the experiment. On day 2, treatment group learned an interfering force field B whereas control group had a day rest. Kinematic analyses showed that control group improved their initial motor performance from day 1 to day 3 but treatment group did not. This behavioral result coincided with an increased higher gamma band power in the electrodes over prefrontal areas on the initial trials of day 3 for control but not treatment group. Intriguingly, this effect vanished with the subsequent re-adaptation on day 3. We suggest that improved re-test performance in a dynamic motor adaptation task is contributed by explicit memory and that gamma bands in the electrodes over the prefrontal cortex are linked to these explicit components. Furthermore, we suggest that the contribution of explicit memory vanishes with the subsequent re-adaptation while task automaticity increases.}, language = {ENG}, journal = {NeuroImage}, author = {Thürer, Benjamin and Stockinger, Christian and Focke, Anne and Putze, Felix and Schultz, Tanja and Stein, Thorsten}, month = oct, year = {2015}, pmid = {26458517}, keywords = {Consolidation, electroencephalography (eeg), Explicit memory, Force field, Reaching movement, Sensorimotor learning} } @article{putze_adaptive_2014, title = {Adaptive cognitive technical systems}, volume = {234}, issn = {1872-678X}, doi = {10.1016/j.jneumeth.2014.06.029}, abstract = {Adaptive cognitive technical systems are capable of sensing the internal state of its user and of adapting its behavior appropriately to those measurements to improve the usability of the system. One important example of such user state is the user's mental workload level. This paper gives an introduction to the topic of workload recognition and adaptation. It reviews the literature on recognition of workload from physiological signals and on how those user state estimates are employed to improve human-machine interaction.}, journal = {Journal of Neuroscience Methods}, author = {Putze, Felix and Schultz, Tanja}, year = {2014}, } @inproceedings{reich_real-time_2011, title = {A Real-Time Speech Command Detector for a Smart Control Room}, booktitle = {Proceedings of 12th {Annual} {Conference} of the {International} {Speech} {Communication} {Association}}, author = {Reich, Daniel and Putze, Felix and Heger, Dominic and Ijsselmuiden, Joris and Stiefelhagen, Rainer and Schultz, Tanja}, year = {2011}, pages = {2641--2644} } @incollection{putze_cognitive_2012, title = {Cognitive dialog systems for dynamic environments: {Progress} and challenges}, booktitle = {Digital {Signal} {Processing} for {In}-{Vehicle} {Systems} and {Safety}}, publisher = {Springer}, author = {Putze, Felix and Schultz, Tanja}, year = {2012}, pages = {133--143} } @inproceedings{putze_combining_2012, address = {Berlin, Germany}, title = {Combining cognitive modeling and {EEG} to predict user behavior in a search task}, booktitle = {Proceedings of the {International} {Conference} on {Cognitive} {Modeling}}, author = {Putze, Felix and Holt, Daniel V. and Funke, Joachim and Schultz, Tanja}, year = {2012}, pages = {303} } @inproceedings{putze_design_2015, address = {New York, NY, USA}, series = {{CHI} '15}, title = {Design and {Evaluation} of a {Self}-{Correcting} {Gesture} {Interface} {Based} on {Error} {Potentials} from {EEG}}, isbn = {978-1-4503-3145-6}, abstract = {Any user interface which automatically interprets the user's input using natural modalities like gestures makes mistakes. System behavior depending on such mistakes will confuse the user and lead to an erroneous interaction flow. The automatic detection of error potentials in electroencephalographic data recorded from a user allows the system to detect such states of confusion and automatically bring the interaction back on track. In this work, we describe the design of such a self-correcting gesture interface, implement different strategies to deal with detected errors, use a simulation approach to analyze performance and costs of those strategies and execute a user study to evaluate user satisfaction. We show that self-correction significantly improves gesture recognition accuracy at lower costs and with higher acceptance than manual correction.}, booktitle = {Proceedings of the 33rd {Annual} {ACM} {Conference} on {Human} {Factors} in {Computing} {Systems}}, publisher = {ACM}, author = {Putze, Felix and Amma, Christoph and Schultz, Tanja}, year = {2015}, keywords = {adaptive interface, error-potentials, gesture recognition, self-correction, simulation, user study}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Putze_GestureError2015.pdf}, pages = {3375--3384}, } @inproceedings{putze_dummy_2015, address = {Hongkong, China}, title = {Dummy {Model} based {Workload} {Modeling}}, booktitle = {Proceedings of {IEEE} {International} {Conference} on {Systems}, {Man} and {Cybernetics}}, author = {Putze, Felix and Pröpper, Robert and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Putze_Dummy2015.pdf}, year = {2015} } @article{putze_hybrid_2014, title = {Hybrid {fNIRS}-{EEG} based classification of auditory and visual perception processes}, volume = {8}, journal = {Frontiers in neuroscience}, author = {Putze, Felix and Hesslinger, Sebastian and Tse, Chun-Yu and Huang, YunYing and Herff, Christian and Guan, Cuntai and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Putze_Hybrid2014.pdf}, year = {2014} } @inproceedings{putze_investigating_2014, address = {Istanbul, Turkey}, title = {Investigating {Intrusiveness} of {Workload} {Adaptation}}, booktitle = {Proceedings of {International} {Conference} on {Multimodal} {Interfaces}}, author = {Putze, Felix and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Putze_Intrusiveness2014.pdf}, year = {2014} } @inproceedings{propper_jam:_2011, title = {{JAM}: {Java}-based {Associative} {Memory}}, copyright = {©2011 Springer Science+Business Media, LLC}, abstract = {In dynamic environments, conversational dialog systems have to deal with ambiguous input, topic shifts and the users’ limited memory resources. Therefore, systems need to model cognitive processes of its users to predict “what is on the user’s mind”. In this paper, we introduce JAM, a cognitive model of associative memory designed for the application in dialog systems. JAM is able to estimate dynamic processes like association, concept drifts and forgetting of information. We describe the data structures and algorithms developed to support these operations and present evaluation results, including the outcome of a survey conducted to compare the results of JAM to human associations.}, language = {en}, urldate = {2014-08-05}, booktitle = {Proceedings of the {Paralinguistic} {Information} and its {Integration} in {Spoken} {Dialogue} {Systems} {Workshop}}, author = {Pröpper, Robert and Putze, Felix and Schultz, Tanja}, month = jan, year = {2011}, keywords = {Language Translation and Linguistics, Signal, Image and Speech Processing, User Interfaces and Human Computer Interaction}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Putze_Memory2011.pdf}, pages = {143--155} } @inproceedings{putze_model-based_2015, address = {Hongkong, China}, title = {Model-based {Evaluation} of {Playing} {Strategies} in a {Memo} {Game} for {Elderly} {Users}}, booktitle = {Proceedings of {IEEE} {International} {Conference} on {Systems}, {Man} and {Cybernetics}}, author = {Putze, Felix and Ehret, Sonja and Miller-Teynor, Heike and Kruse, Andreas and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Putze_Memo2015.pdf}, year = {2015} } @inproceedings{putze_model-based_2014, address = {Hamburg, Germany}, title = {Model-based {Identification} of {EEG} {Markers} for {Learning} {Opportunities} in an {Associative} {Learning} {Task} with {Delayed} {Feedback}}, booktitle = {Proceedings of 24th {International} {Conference} on {Artificial} {Neural} {Networks}}, author = {Putze, Felix and Holt, Daniel V. and Schultz, Tanja and Funke, Joachim}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Putze_Learning2014.pdf}, year = {2014} } @inproceedings{hild_spatio-temporal_2014, title = {Spatio-{Temporal} {Event} {Selection} in {Basic} {Surveillance} {Tasks} using {Eye} {Tracking} and {EEG}}, booktitle = {Proceedings of the 7th {Workshop} on {Eye} {Gaze} in {Intelligent} {Human} {Machine} {Interaction}: {Eye}-{Gaze} \& {Multimodality}}, publisher = {ACM}, author = {Hild, Jutta and Putze, Felix and Kaufman, David and Kühnle, Christian and Schultz, Tanja and Beyerer, Jürgen}, year = {2014}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Putze_Gaze2014.pdf}, pages = {3--8} } @book{schultz_technische_2014a, title = {Technische {Unterstuetzung} fuer {Menschen} mit {Demenz} : {Symposium} 30.09. - 01.10.2013}, isbn = {978-3-7315-0258-6}, shorttitle = {Technische {Unterstuetzung} fuer {Menschen} mit {Demenz}}, language = {de}, publisher = {KIT Scientific Publishing}, author = {Schultz, Tanja and Putze, Felix and Kruse, Andreas}, year = {2014} } @incollection{schultz_technische_2014, address = {Karlsruhe, Germany}, title = {Technische {Unterstützung} für {Menschen} mit {Demenz} - {Ein} Überblick}, booktitle = {Technische {Unterstützung} für {Menschen} mit {Demenz}}, publisher = {KIT Scientific Publishing}, author = {Schultz, Tanja and Putze, Felix and Mikut, Ralf and Weinberger, Nora and Boch, Katrin and Schmitt, Eric and Decker, Michael and Lind-Matthäus, Dagmar and Metz, Brigitte}, year = {2014}, pages = {1--18} } @incollection{mikut_data-mining-methoden_2014, address = {Karlsruhe, Germany}, title = {Data-{Mining}-{Methoden} für die {Demenzforschung}: {Stand} und {Potentiale}}, booktitle = {Technische {Unterstützung} für {Menschen} mit {Demenz}}, publisher = {KIT Scientific Publishing}, author = {Mikut, Ralf and Reischl, Markus and Putze, Felix and Schultz, Tanja}, year = {2014}, pages = {89--104} } @incollection{putze_aktiv:_2014, address = {Karlsruhe, Germany}, title = {{AKTIV}: {Multimodal} {Interaction} {System} to {Engage} {Patients} with {Dementia}}, booktitle = {Technische {Unterstützung} für {Menschen} mit {Demenz}}, publisher = {KIT Scientific Publishing}, author = {Putze, Felix and Tapaswi, Makarand and Martinez, Manel and Telaar, Dominic and Heger, Dominic and Sarfraz, Saquib and Schultz, Tanja and Stiefelhagen, Rainer}, year = {2014}, pages = {105--122} } @inproceedings{escaida_navarro_telemanipulation_2015, address = {Hamburg, Germany}, title = {Telemanipulation with {Force}-{Based} {Display} of {Proximity} {Fields}}, booktitle = {Proceedings of {IEEE}/{RSJ} {International} {Conference} on {Intelligent} {Robots} and {Systems}}, author = {Escaida Navarro, Stefan and Heger, Franz and Putze, Felix and Beyl, Tim and Schultz, Tanja and Hein, Björn}, year = {2015} } @inproceedings{diener2015direct, title={Direct Conversion from Facial Myoelectric Signals to Speech using Deep Neural Networks}, author={Diener, Lorenz and Janke, Matthias and Schultz, Tanja}, note={IJCNN 2015}, booktitle={International Joint Conference on Neural Networks}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Direct_Conversion_from_Facial_Myoelectric_Signals_to_Speech_using_Deep_Neural_Networks.pdf}, abstract={This paper presents our first results using Deep Neural Networks for surface electromyographic (EMG) speech synthesis. The proposed approach enables a direct mapping from EMG signals captured from the articulatory muscle movements to the acoustic speech signal. Features are processed from multiple EMG channels and are fed into a feed forward neural network to achieve a mapping to the target acoustic speech output. We show that this approach is feasible to generate speech output from the input EMG signal and compare the results to a prior mapping technique based on Gaussian mixture models. The comparison is conducted via objective Mel-Cepstral distortion scores and subjective listening test evaluations. It shows that the proposed Deep Neural Network approach gives substantial improvements for both evaluation criteria.}, keywords={electromyography, silent speech interface, deep neural networks}, pages={1--7}, doi={10.1109/IJCNN.2015.7280404}, year={2015}, } @INPROCEEDINGS{HennrichEMBC2015, author={Hennrich, J. and Herff, C. and Heger, D. and Schultz, T.}, booktitle={Engineering in Medicine and Biology Society (EMBC), 2015 37th Annual International Conference of the IEEE}, title={Investigating Deep Learning for Fnirs Based BCI}, year={2015}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/EMBC2015_Hennrich.pdf}, abstract={Functional Near infrared Spectroscopy (fNIRS) is a relatively young modality for measuring brain activity which has recently shown promising results for building Brain Computer Interfaces (BCI). Due to its infancy, there are still no standard approaches for meaningful features and classifiers for single trial analysis of fNIRS. Most studies are limited to established classifiers from EEG-based BCIs and very simple features. The feasibility of more complex and powerful classification approaches like Deep Neural Networks has, to the best of our knowledge, not been investigated for fNIRS based BCI. These networks have recently become increasingly popular, as they outperformed conventional machine learning methods for a variety of tasks, due in part to advances in training methods for neural networks. In this paper, we show how Deep Neural Networks can be used to classify brain activation patterns measured by fNIRS and compare them with previously used methods.}, keywords={Neural networks in biosignal processing and classification, Biomedical signal classification}, month={Aug}, } @INPROCEEDINGS{7146565, author={Heger, D. and Herff, C. and Putze, F. and Schultz, T.}, booktitle={Neural Engineering (NER), 2015 7th International IEEE/EMBS Conference on}, title={Joint optimization for discriminative, compact and robust Brain-Computer Interfacing}, year={2015}, pages={82-85}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ner_2015_paper_heger.pdf}, abstract={We present a new pattern recognition framework for Brain-Computer Interfacing that learns discriminative brain activity patterns, compact modeling, and robustness against signal variabilities by a single joint optimization. We present an algorithm based on the Alternating Direction Method of Multipliers, which finds an optimal solution for this approach extremely efficiently. A first evaluation using a publicly available EEG motor imagery data corpus with 105 subjects shows that our framework outperformed state-of-the-art methods and successfully performed subject transfer.}, keywords={brain-computer interfaces;electroencephalography;medical signal processing;neurophysiology;optimisation;pattern recognition;EEG motor imagery data corpus;alternating direction method of multipliers;compact modeling;discriminative brain activity patterns;pattern recognition framework;robust brain-computer interfacing;single joint optimization;Brain;Electroencephalography;Feature extraction;Optimization;Pattern recognition;Robustness;Training}, doi={10.1109/NER.2015.7146565}, month={April},} @INPROCEEDINGS{7146546, author={Herff, C. and Fortmann, O. and Chun-Yu Tse and Xiaoqin Cheng and Putze, F. and Heger, D. and Schultz, T.}, booktitle={Neural Engineering (NER), 2015 7th International IEEE/EMBS Conference on}, title={Hybrid fNIRS-EEG based discrimination of 5 levels of memory load}, year={2015}, pages={5-8}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ner_2015_paper_cherff.pdf}, abstract={In this study, we show that both electroencephalograhy (EEG) and functional Near-Infrared Spectroscopy (fNIRS) can be used to discriminate between 5 levels of memory load. We induce memory load with the memory updating task, which is known to robustly generate memory load and allows us to define 5 different levels of load. Typical experiments only discriminate between low and high workload or up to a maximum of three classes. To the best of our knowledge, the memory updating task has not been used in combination with brain activity measurements before. Here, accuracies of up to 93% are achieved for the binary classification between very high and very low workload. On average, two levels of workload could be discriminated with 74% accuracy. Classification between the full five classes yielded 44% accuracy on average. Despite the fact that EEG results consistently outperformed the results obtained with fNIRS, we could show that the feature-level fusion of both modalities increased robustness of classification results. A reliable discrimination between different levels of memory load could be used to adapt user interfaces or present the right amount of information to a learner.}, keywords={cognition;electroencephalography;feature extraction;infrared spectroscopy;medical signal processing;neurophysiology;sensor fusion;signal classification;user interfaces;5-level memory load discrimination;binary classification accuracy;brain activity measurements;classification robustness;electroencephalograhy;feature-level fusion;five-class classification accuracy;functional near-infrared spectroscopy;high memory workload discrimination;hybrid fNIRS-EEG based discrimination;low memory workload discrimination;memory load generation;memory updating task;three-class workload discrimination;two-level workload discrimination accuracy;user interface;Accuracy;Brain;Electrodes;Electroencephalography;Feature extraction;Robustness;Spectroscopy}, doi={10.1109/NER.2015.7146546}, month={April},} @inproceedings{diener2015codebook, title={Codebook Clustering for Unit Selection Based EMG-to-Speech Conversion}, author={Diener, Lorenz and Janke, Matthias and Schultz, Tanja}, note={Interspeech 2015}, booktitle={Sixteenth Annual Conference of the International Speech Communication Association}, pages={2420--2424}, abstract={This paper reports on our recent advances in using Unit Selection to directly synthesize speech from facial surface electromyographic (EMG) signals generated by movement of the articulatory muscles during speech production. We achieve a robust Unit Selection mapping by using a more sophisticated unit codebook. This codebook is generated from a set of base units using a two stage unit clustering process. The units are first clustered based on the audio and afterwards on the EMG feature vectors they cover, and a new codebook is generated using these cluster assignments. We evaluate different cluster counts for both stages and revisit our evaluation of unit sizes in light of this clustering approach. Our final system achieves a significantly better Mel-Cepstral distortion score than the Unit Selection based EMG-to-Speech conversion system from our previous work while, due to the reduced codebook size, taking less time to perform the conversion.}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Codebook_Clustering_for_Unit_Selection Based_EMG-to-Speech_Conversion.pdf}, keywords={electromyography, silent speech interface, unit selection}, year={2015} } @comment{Old page: http://csl.anthropomatik.kit.edu/reports_1307.php} @comment{Additional data: LTI Technical Report CMU-LTI-07-017, Carnegie Mellon University, Pittsburgh PA, USA} @techreport{laskowski2007a, year={2007}, title={A Supervised Factorial Acoustic Model for Simultaneous Multiparticipant Vocal Activity Detection in Close-Talk Microphone Recordings of Meetings}, author={Laskowski, Kornel and Burger, Susanne} } @comment{Old page: http://csl.anthropomatik.kit.edu/1855_2899.php} @mastersthesis{sun2014prosodic, school={Karlsruher Institut für Technologie}, title={Prosodic Features for Code-Switching Speech Recognition}, year={2014}, supervisor={Telaar, Dominic and Vu, Thang and Schultz, Tanja}, author={Sun, Jing} } @comment{Old page: http://csl.anthropomatik.kit.edu/1855_2898.php} @mastersthesis{adel2014integration, school={Karlsruher Institut für Technologie}, title={Integration of Syntactic and Semantic Features into Statistical Code-Switching Language Models}, year={2014}, supervisor={Telaar, Dominic and Vu, Thang and Kirchhoff, Katrin and Schultz, Tanja}, author={Adel, Heike} } @comment{Old page: http://csl.anthropomatik.kit.edu/1855_2688.php} @mastersthesis{schulte2013kompensation, school={Karlsruher Institut für Technologie}, title={Kompensation unterschiedlicher Elektrodenpositionierungen in der EMG-basierten Sprachverarbeitung}, year={2013}, supervisor={Wand, Michael and Janke, Matthias and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/MA_Schulte-FinalVersion.pdf}, author={Schulte, Christopher} } @comment{Old page: http://csl.anthropomatik.kit.edu/1855_2809.php} @mastersthesis{waldkirch2013entwicklung, school={Karlsruher Institut für Technologie}, title={Entwicklung von Strategien zur Fehlererkennung und Fehlerbehandlung für ein gestenbasiertes Eingabesystem}, year={2013}, supervisor={Putze, Felix and Schultz, Tanja}, author={Waldkirch, Christian} } @comment{Old page: http://csl.anthropomatik.kit.edu/1855_2808.php} @mastersthesis{colling2013recognition, school={Karlsruher Institut für Technologie}, year={2013}, title={Recognition of Player Deficits using Game-Triggered Intervention and Bayesian Networks}, supervisor={Putze, Felix and Schultz, Tanja}, author={Colling, Steven} } @comment{Old page: http://csl.anthropomatik.kit.edu/1855_2062.php} @mastersthesis{müller2012implementierung, school={Karlsruher Institut für Technologie}, title={Implementierung und Evaluation session-invarianter EEG-basierter Workload Erkennung}, year={2012}, supervisor={Putze, Felix and Schultz, Tanja}, author={Müller, Markus} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_2934.php} @comment{Additional data:

Video

 

} @ARTICLE{10.3389/fnins.2015.00217, AUTHOR={Herff, Christian and Heger, Dominic and de Pesters, Adriana and Telaar, Dominic and Brunner, Peter and Schalk, Gerwin and Schultz, Tanja}, TITLE={Brain-to-text: Decoding spoken phrases from phone representations in the brain}, JOURNAL={Frontiers in Neuroscience}, VOLUME={9}, YEAR={2015}, NUMBER={217}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/fnins-09-00217.pdf}, DOI={10.3389/fnins.2015.00217}, ISSN={1662-453X} , ABSTRACT={It has long been speculated whether communication between humans and machines based on natural speech related cortical activity is possible. Over the past decade, studies have suggested that it is feasible to recognize isolated aspects of speech from neural signals, such as auditory features, phones or one of a few isolated words. However, until now it remained an unsolved challenge to decode continuously spoken speech from the neural substrate associated with speech and language processing. Here, we show for the first time that continuously spoken speech can be decoded into the expressed words from intracranial electrocorticographic (ECoG) recordings.Specifically, we implemented a system, which we call Brain-To-Text that models single phones, employs techniques from automatic speech recognition (ASR), and thereby transforms brain activity while speaking into the corresponding textual representation. Our results demonstrate that our system can achieve word error rates as low as 25% and phone error rates below 50%. Additionally, our approach contributes to the current understanding of the neural basis of continuous speech production by identifying those cortical regions that hold substantial information about individual phones. In conclusion, the Brain-To-Text system described in this paper represents an important step toward human-machine communication based on imagined speech.} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_2925.php} @article{adel2015syntactic, number={3}, title={Syntactic and Semantic Features For Code-Switching Factored Language Models}, volume={23}, year={2015}, journal={IEEE/ACM Transactions on Audio, Speech and Language Processing}, author={Adel, Heike and Vu, Ngoc Thang and Kirchhoff, Katrin and Telaar, Dominic and Schultz, and Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_2920.php} @article{stahlberg2014word, title={Word Segmentation and Pronunciation Extraction from Phoneme Sequences Through Cross-Lingual Word-to-Phoneme Alignment}, year={2014}, journal={Computer Speech & Language, Elservier}, author={Stahlberg, Felix and Schlippe, Tim and Vogel, Stephan and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_2900.php} @article{wand2013application, title={Application of Electrode Arrays for Artifact Removal in an Electromyographic Silent Speech Interface}, pages={300 - 312}, year={2013}, note={BIOSTEC 2013}, journal={Biomedical Engineering Systems and Technologies International Joint Conference, Barcelona, Spain (Also in: Revised Selected Papers Communications in Computer and Information Science, Vol. 452)}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/WandJankeSchultz_Application_Electrode_Arrays.pdf}, abstract={An electromygraphic (EMG) Silent Speech Interface is a system which recognizes speech by capturing the electric potentials of the human articulatory muscles, thus enabling the user to communicate silently. This study deals with the introduction of multi-channel electrode arrays to the EMG recording system, which requires meticulous dealing with the resulting high-dimensional data. As a first application of the technology, Independent Component Analysis (ICA) is applied for automated artifact detection and removal. Without the artifact removal component, the system achieves optimal average Word Error Rates of 40.1% for 40 training sentences and 10.9% for 160 training sentences on EMG signals of audible speech. On a subset of the corpus, we evaluate the ICA artifact removal method, improving the Word Error Rate by 10.7% relative.}, author={Wand, Michael and Janke, Matthias and Heistermann, Till and Schulte, Christopher and , and Himmelsbach, Adam and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_2874.php} @article{wand2014tackling, volume={61}, year={2014}, title={Tackling Speaking Mode Varieties in EMG-Based Speech Recognition}, number={10}, journal={IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING}, abstract={An electromyographic (EMG) silent speech recognizer is a system that recognizes speech by capturing the electric potentials of the human articulatory muscles, thus enabling the user to communicate silently. After having established a baseline EMG-based continuous speech recognizer, in this paper, we investigate speaking mode variations, i.e., discrepancies between audible and silent speech that deteriorate recognition accuracy. We introduce multimode systems that allow seamless switching between audible and silent speech, investigate different measures which quantify speaking mode differences, and present the spectral mapping algorithm, which improves the word error rate (WER) on silent speech by up to 14.3% relative. Our best average silent speech WER is 34.7%, and our best WER on audibly spoken speech is 16.8%.}, author={Wand, Michael and Schultz, Matthias Janke; Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_2752.php} @article{doi:10.1080/2326263X.2014.912884, author = {Dominic Heger and Christian Herff and Felix Putze and Reinhard Mutter and Tanja Schultz}, title = {Continuous affective states recognition using functional near infrared spectroscopy}, journal = {Brain-Computer Interfaces}, volume = {1}, number = {2}, pages = {113-125}, year = {2014}, doi = {10.1080/2326263X.2014.912884}, URL = {http://www.csl.uni-bremen.de/cms/images/documents/publications/BCI_Heger2014.pdf}, eprint = { http://dx.doi.org/10.1080/2326263X.2014.912884}, abstract = {Monitoring the affective states of a person can be highly relevant for numerous disciplines, including adaptive user interfaces, entertainment, ergonomics, medicine and therapy. In many situations, the affective state of a user is not easily observable from outside by audio or video, but may be identified by a brain-computer interface (BCI). Functional near-infrared spectroscopy (fNIRS) is a brain imaging modality gaining rising attention in the BCI community. However, fNIRS emotion recognition studies have only analyzed stimulus-locked effects. For realistic human-machine interaction scenarios, the point of time of an emotion-triggering event and the time span of an affective state are unknown. In this paper, we investigate a BCI that monitors the affective states of the user continuously over time (i.e. asynchronous BCI). In our study, fNRIS signals from eight subjects have been recorded at eight prefrontal locations in response to three different classes of affect induction by emotional audio-visual stimuli plus a neutral class. Our system evaluates short windows of 5 s length to continuously recognize affective states. We analyze hemodynamic responses, present a careful evaluation of binary classification tasks, compare time-domain and wavelet-based signal features, and investigate classification accuracies over time. } } @comment{Old page: http://csl.anthropomatik.kit.edu/books_2671.php} @ARTICLE{10.3389/fnhum.2013.00935, AUTHOR={Herff, Christian and Heger, Dominic and Fortmann, Ole and Hennrich, Johannes and Putze, Felix and Schultz, Tanja}, TITLE={Mental workload during n-back task - quantified in the prefrontal cortex using fNIRS}, JOURNAL={Frontiers in Human Neuroscience}, VOLUME={7}, YEAR={2014}, NUMBER={935}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/fnhum_cherff.pdf}, DOI={10.3389/fnhum.2013.00935}, ISSN={1662-5161} , ABSTRACT={When interacting with technical systems, users experience mental workload. Particularly in multitasking scenarios (e.g., interacting with the car navigation system while driving) it is desired to not distract the users from their primary task. For such purposes, human-machine interfaces (HCIs) are desirable which continuously monitor the users' workload and dynamically adapt the behavior of the interface to the measured workload. While memory tasks have been shown to elicit hemodynamic responses in the brain when averaging over multiple trials, a robust single trial classification is a crucial prerequisite for the purpose of dynamically adapting HCIs to the workload of its user. The prefrontal cortex (PFC) plays an important role in the processing of memory and the associated workload. In this study of 10 subjects, we used functional Near-Infrared Spectroscopy (fNIRS), a non-invasive imaging modality, to sample workload activity in the PFC. The results show up to 78% accuracy for single-trial discrimination of three levels of workload from each other. We use an n-back task (n ? {1, 2, 3}) to induce different levels of workload, forcing subjects to continuously remember the last one, two, or three of rapidly changing items. Our experimental results show that measuring hemodynamic responses in the PFC with fNIRS, can be used to robustly quantify and classify mental workload. Single trial analysis is still a young field that suffers from a general lack of standards. To increase comparability of fNIRS methods and results, the data corpus for this study is made available online.} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_2653.php} @article{amma2013airwriting, number={2}, title={Airwriting: Bringing text entry to wearable computers}, volume={20}, pages={50-55}, year={2013}, doi={10.1145/2540048 }, journal={XRDS: Crossroads, The ACM Magazine for students}, author={Amma, Christoph and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_2650.php} @article{schultz2013biosignale, number={11}, title={Biosignale-basierte Mensch-Maschine-Schnittstellen}, year={2013}, volume={61}, pages={760 - 769}, journal={at - Automatisierungstechnik, 2013}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Biosignals.TSchultz.10012014.pdf}, author={Schultz, Tanja and Amma, Christoph and Heger, Dominic and Putze, Felix and Wand, Michael} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_2514.php} @article{besacier2014automatic, volume={56}, pages={85-100}, year={2014}, title={Automatic Speech Recognition for Under-resourced Languages: A Survey}, journal={Speech Communication, January 2014}, author={Besacier, Laurent and Barnard, Etienne and Karpov, Alexey and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_2396.php} @article{schlippe2014web, title={Web-based Tools and Methods for Rapid Pronunciation Dictionary Creation}, volume={56}, pages={101}, year={2014}, journal={Speech Communication, 118, January 2014.}, author={Schlippe, Tim and Ochs, Sebastian and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_2219.php} @article{amma2013airwriting, year={2013}, doi={10.1007/s00779-013-0637-3}, title={Airwriting: a wearable handwriting recognition system}, journal={Personal and Ubiquitous Computing, available online first with}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/AmmaGeorgiSchultz_PUC2013.pdf}, author={Amma, Christoph and Georgi, Marcus and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_1982.php} @article{heger2011an, number={4}, year={2011}, pages={415-425}, volume={3}, title={An EEG Adaptive Information System for an Empathic Robot}, journal={International Journal of Social Robotics, Special Issue Towards an Effective Design of Social Robot, (2011)}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/paper.pdf}, author={Heger, Dominic and Putze, Felix and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_1032.php} @article{tam2008bilingual, year={2008}, doi={10.1007/s10590-008-9045-2}, title={Bilingual-LSA based Adaptation for Statistical Machine Translation}, journal={Machine Translation, Springer Netherlands, preprint}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/MT2008-TamLaneSchultz.pdf}, author={Tam, Yik-Cheung and Lane, Ian and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_1043.php} @article{schultz2001language, year={2001}, volume={35}, pages={31-51}, title={Language Independent and Language Adaptive Acoustic Modeling for Speech Recognition}, number={1-2}, journal={Speech Communication}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SchultzSpecom26062000.ps.gz}, author={Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_1035.php} @article{stein2008kinematische, title={Kinematische Analyse menschlicher Alltagsbewegungen für die Mensch-Maschine-Interaktion}, pages={49-58)}, year={2008}, journal={In J. Edelmann-Nusser, E. F. Moritz, V. Senner, & K. Witte (2009). Sporttechnologie zwischen Theorie und Praxis V (. Aachen: Shaker Verlag.}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Sporttechnologie2008.pdf}, author={Stein, Thorsten and Fischer, Andreas and Boesnach, Ingo and Gehrig, Dirk and Köhler, Hildegard and Schwameder, Hermann} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_1029.php} @article{schultz2010modeling, number={4}, volume={52}, pages={341 - 353}, year={2010}, title={Modeling Coarticulation in EMG-based Continuous Speech Recognition}, journal={Speech Communication Journal}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SchultzWand-SCJ10-ModelingCoarticulation.pdf}, author={Schultz, Tanja and Wand, Michael} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_1040.php} @article{schultz2006multilingual, title={Multilingual Speech Processing}, year={2006}, journal={Elsevier, Academic Press, ISBN 13: 978-0-12-088501-5}, author={Schultz, Tanja and Kirchhoff, Katrin} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_1044.php} @article{waibel2000multilingual, year={2000}, title={Multilingual Speech Recognition}, journal={Verbmobil: Foundations of Speech-to-Speech Translation, Wolfgang Wahlster (Ed.), Springer Verlag}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/WSMmulti.6.ps.gz}, author={Waibel, Alex and Soltau, Hagen and Schultz, Tanja and Schaaf, Thomas and Metze, Florian} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_1037.php} @article{schultz2007speaker, year={2007}, title={Speaker Characteristics}, journal={In: C. Müller (Ed.) Speaker Classification, Lecture Notes in Computer Science / Artificial Intelligence, Springer, Heidelberg - Berlin - New York, Volume 4343.}, author={Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_1046.php} @article{geutner1995integrating, title={Integrating Different Learning Approaches into a Multilingual Spoken Language Translation System}, pages={117-131}, year={1995}, journal={Connectionist, statistical and symbolic approaches to learning for natural language processing, Lecture Notes in Artificial Intelligence, Springer}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/nlp_learning.ps.gz}, author={Geutner, Petra and Suhm, B and Buø, F.D and Kemp, Thomas and Tomokiyo-Mayfield, Laura and McNair, A.E and Rogina, Ivica and Schultz, Tanja and Sloboda, T and Ward, W and Woszczyna, Monika and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_1030.php} @article{denby2010silent, number={4}, title={Silent Speech Interfaces}, year={2010}, volume={52}, pages={270 - 287}, journal={Speech Communication Journal}, author={Denby, Bruce and Schultz, Tanja and Honda, Kiyoshi and Hueber, Thomas and Gilbert, Jim and Brumberg, Jon} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_1033.php} @article{schultz2008automatic, title={Automatic Speech Recognition based on Electromyographic Biosignals}, year={2008}, journal={Selected from the BIOSTEC full papers to be published in:Communications in Computer and Information Science (CCIS) series publishedby Springer}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/CCIS08-JouSchultz-submitted.pdf}, author={Schultz, Tanja and Jou, Szu-Chen (Stan)} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_1031.php} @article{wand2010speaker, year={2010}, title={Speaker-Adaptive Speech Recognition Based on Surface Electromyography}, journal={Biomedical Engineering Systems and TechnologiesInternational Joint Conference, BIOSTEC2009, Porto, Portugal, January 14-17, 2009, Revised Selected PapersCommunications in Computer and Information Science , Vol. 52}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/WandSchultz_SpeakerAdaptiveSpeechRecognition_CCIS.pdf}, author={Wand, Michael and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_1038.php} @article{paulik2007translating, title={Translating language with technology's help}, year={2007}, pages={30 - 35}, volume={26}, journal={IEEE potentials - the magazine for high-tech inovators, No.3, MAY/JUNE 2007}, author={Paulik, Matthias and Stüker, Sebastian and Fügen, Christian and Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_1045.php} @article{waibel2000multilinguality, title={Multilinguality in Speech and Spoken Language Systems}, year={2000}, pages={1297-1313}, volume={88(8)}, journal={Proceedings of the IEEE, Special Issue on Spoken Language Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/IEEE1July2002.ps}, author={Waibel, Alex and Geutner, Petra and Tomokiyo-Mayfield, Laura and Schultz, Tanja and Woszczyna, Monika} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_1034.php} @article{fung2008multilingual, title={Multilingual Spoken Language Processing}, year={2008}, journal={IEEE Signal Processing Magazine [89] May 2008}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/810_IEEESignal_Processing.pdf}, author={Fung, Pascale and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_1042.php} @article{jekat2001evaluation, year={2001}, title={Evaluation Sprachverarbeitender Systeme}, journal={Computerlinguistik und Sprachtechnologie, Ralf Klabunde et.al (Ed.), Spektrum - Akademischer Verlag, Oktober 2001. ISNB 3827410274}, author={Jekat, Susanne and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_1039.php} @article{schultz2007multilingual, year={2007}, title={Multilingual Speech Processing - Challenges and Solutions}, number={1}, journal={MultiLingual, #85 Volume 18 2007.MultiLingual Computing, Inc., 319 North First Avenue, Suite 2, Sandpoint, Idaho 83864-1495 USA}, author={Schultz, Tanja and Kirchhoff, Katrin} } @comment{Old page: http://csl.anthropomatik.kit.edu/books_1041.php} @article{schultz2006flexible, title={Flexible Speech Translation Systems}, year={2006}, journal={IEEE Transactions on Audio, Speech, and Language Processing, Vol 14(2)}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Schultz-IEEE2006.pdf}, author={Schultz, Tanja and Black, Alan W and Vogel, Stephan and Woszczyna, Monika} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_2731.php} @studentresearchproject{breiter2014rapid, school={Karlsruher Institut für Technologie}, title={Rapid Bootstrapping of Haitian Creole Large Vocabulary Continuous Speech Recognition}, year={2014}, supervisor={Schlippe, Tim and Vu, Ngoc Thang and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SA_WojtekBreiter.pdf}, author={Breiter, Wojtek} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_2819.php} @studentresearchproject{majarle2014klassifizierung, school={Karlsruher Institut für Technologie}, year={2014}, title={Klassifizierung EEG basierter ereigniskorrelierter Potentiale aus visuellen und auditiven Aufgaben}, supervisor={Putze, Felix and Schultz, Tanja}, author={Majarle, Dimitri} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_2820.php} @studentresearchproject{zwar2014confidence, school={Karlsruher Institut für Technologie}, title={Confidence-based Methods to Improve Reliability and Fusion Performance of EEG-based Workload Recognition System}, year={2014}, supervisor={Putze, Felix and Schultz, Tanja}, author={Zwar, Lena} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_2836.php} @studentresearchproject{terziyska2013integrating, school={Karlsruher Institut für Technologie}, title={Integrating MVAR based Connectivity Measures into EEG Single-trial Prediction}, year={2013}, supervisor={Heger, Dominik}, author={Terziyska, Emiliyana} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_2821.php} @studentresearchproject{zairi2013managemant, school={Karlsruher Institut für Technologie}, year={2013}, title={Managemant of the Text and Speech Resources in the Rapid Language Adaptation Toolkit}, supervisor={Schlippe, Tim and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SA_AdneneZairi.pdf}, author={Zairi, Adnene} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_2428.php} @studentresearchproject{lemcke2013keynounce, school={Karlsruher Institut für Technologie}, title={Keynounce - A Game for Pronunciation Generation through Crowdsourcing}, year={2013}, supervisor={Schlippe, Tim and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SA-Daniel-Lemcke.pdf}, author={Lemcke, Daniel} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_2818.php} @studentresearchproject{kintz2013datenanalyse, school={Karlsruher Institut für Technologie}, title={Datenanalyse zur Vorbereitung einer Workload-Komponente für ACT-R}, year={2013}, supervisor={Putze, Felix and Schultz, Tanja}, author={Kintz, Dorothea} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_2429.php} @studentresearchproject{quaschningk2013analyzing, school={Karlsruher Institut für Technologie}, title={Analyzing Single and Combined G2P Converter Outputs over Training Data}, year={2013}, supervisor={Schlippe, Tim and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SA_WolfQuaschningk.pdf}, author={Quaschningk, Wolf} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_2816.php} @studentresearchproject{heßlinger2012analyzing, school={Karlsruher Institut für Technologie}, year={2012}, title={Analyzing n-back EEG Data with Auditory and Visual Stimuli using ICA-based Spatial Filtering}, supervisor={Putze, Felix and Schultz, Tanja}, author={Heßlinger, and Sebastian, } } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_2812.php} @studentresearchproject{bieler2011analyse, school={Karlsruher Institut für Technologie}, title={Analyse und Wirkung von Musik anhand von EEG-Daten}, year={2011}, supervisor={Putze, Felix and Schultz, Tanja}, author={Bieler, Jochen} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_2051.php} @studentresearchproject{gren2011enhancing, school={Karlsruher Institut für Technologie}, year={2011}, title={Enhancing Language Models for ASR using RSS Feeds}, supervisor={Schlippe, Tim and Vu, Ngoc Thang and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SA_LukaszGren.pdf}, author={Gren, Lukasz} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_2073.php} @studentresearchproject{putze2011design, school={Karlsruher Institut für Technologie}, year={2011}, title={Design und Analyse eines computergestützten Flirtexperiments}, supervisor={Schultz, Tanja}, author={Putze, Susanne} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_2050.php} @studentresearchproject{djomgang2011hausa, school={Karlsruher Institut für Technologie}, title={Hausa Large Vocabulary Continuous Speech Recognition}, year={2011}, supervisor={Schlippe, Tim and Vu, Ngoc Thang and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SA_EdyGuevaraKomgang.pdf}, author={Djomgang, Edy Guevara Komgang} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_1289.php} @studentresearchproject{mihaylova2010an, school={Karlsruher Institut für Technologie}, year={2010}, title={An Architecture of a Telephone-based System for Speech Data Collection}, supervisor={Schlippe, Tim and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SA_ZlatkaMihaylova.pdf}, author={Mihaylova, Zlatka} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_1287.php} @studentresearchproject{kara2010session, school={Karlsruher Institut für Technologie}, year={2010}, title={Session-adaptive Speech Recognition based on Surface Electromyography}, supervisor={Wand, Michael and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SA_Elkara.pdf}, author={Kara, Kais} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_2049.php} @studentresearchproject{gebhardt2009multilingual, school={Karlsruher Institut für Technologie}, title={Multilingual Acoustic Model Combination using Rapid Language Adaption Toolkit (RLAT)}, year={2009}, supervisor={Schultz, Tanja and Schlippe, Tim}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SA_JanGebhardt.pdf}, author={Gebhardt, Jan} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_1288.php} @studentresearchproject{jarvis2010multimodale, school={Karlsruher Institut für Technologie}, year={2010}, title={Multimodale biosignalbasierte Workloaderkennung im Fahrzeug}, supervisor={Putze, Felix and Schultz, Tanja}, author={Jarvis, Jan-Philip} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_2072.php} @studentresearchproject{schenkel2009mutual, school={Karlsruher Institut für Technologie}, year={2009}, title={Mutual information feature selection for speaker recognition}, supervisor={Schultz, Tanja}, author={Schenkel, Peter} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_2811.php} @studentresearchproject{krupicka2009selection, school={Karlsruher Institut für Technologie}, year={2009}, title={Selection and Implementation of a Cognitive Memory Model}, supervisor={Putze, Felix and Schultz, Tanja}, author={Krupicka, Florian} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_1291.php} @studentresearchproject{Öxler2009planung, school={Karlsruher Institut für Technologie}, title={Planung und Aufbau eines realistischen Fahrsimulators für die Untersuchung von kognitiven Dialogsystemen - Schwerpunkt Software}, year={2009}, supervisor={Putze, Felix and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/studienarbeit_rikard_01.pdf}, author={Öxler, Rikard} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_1292.php} @studentresearchproject{reinhold2009planung, school={Karlsruher Institut für Technologie}, year={2009}, title={Planung und Aufbau eines realistischen Fahrsimulators für die Untersuchung von kognitiven Dialogsystemen - Schwerpunkt Hardware}, supervisor={Putze, Felix and Schultz, Tanja}, author={Reinhold, Frieder} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_1290.php} @studentresearchproject{he2009automatic, school={Karlsruher Institut für Technologie}, title={Automatic Pronunciation Dictionary Generation from Wiktionary and Wikipedia}, year={2009}, supervisor={Schlippe, Tim and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SA_QingyueHe.pdf}, author={He, Qingyue} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_2071.php} @studentresearchproject{telaar2008extractive, school={Karlsruher Institut für Technologie}, year={2008}, title={Extractive Speech Summarization on Mandarin Lectures}, supervisor={Schultz, Tanja}, author={Telaar, Dominic} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_1294.php} @studentresearchproject{porbadnigk2008eeg, school={Karlsruher Institut für Technologie}, title={EEG-based Speech Recognition: Impact of Experimental Design on Performance}, year={2008}, supervisor={Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SA-Porbadnigk.pdf}, author={Porbadnigk, Anne} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_1293.php} @studentresearchproject{schaaff2008challenges, school={Karlsruher Institut für Technologie}, year={2008}, title={Challenges on Emotion Induction with the International Affective Picture System}, supervisor={Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SA-Schaaff.pdf}, author={Schaaff, Kristina} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_1295.php} @studentresearchproject{sitto2008evaluierung, school={Karlsruher Institut für Technologie}, title={Evaluierung von Algorithmen zur automatischen Segmentierung menschlicher Bewegungen}, year={2008}, supervisor={Gehrig, Dirk and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SA-Dirk.pdf}, author={Sitto, Sandro} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_2070.php} @studentresearchproject{wand2007wavelet, school={Karlsruher Institut für Technologie}, title={Wavelet-based Preprocessing of Electroencephalographic and Electromyographic Signals for Speech Recognition}, year={2007}, supervisor={Schultz, Tanja}, author={Wand, Michael} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_1296.php} @comment{Additional data: Institut für Theoretische Informatik, Lehrstuhl Prof. Waibel, Universität Karlsruhe} @studentresearchproject{wand2007wavelet, school={Karlsruher Institut für Technologie}, year={2007}, title={Wavelet-based Processing of EEG and EMG Signals for Speech Recognition}, supervisor={Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SA-Wand.pdf}, author={Wand, Michael} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_1297.php} @comment{Additional data: Institut für Theoretische Informatik, Lehrstuhl Prof. Waibel, Universität Karlsruhe} @studentresearchproject{callies2006further, school={Karlsruher Institut für Technologie}, year={2006}, title={Further Investigations on Unspoken Speech}, supervisor={Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SA-Callies.pdf}, author={Callies, Jan Peter} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_1298.php} @comment{Additional data: Institut für Theoretische Informatik, Lehrstuhl Prof. Waibel, Universität Karlsruhe} @studentresearchproject{mircheva2006bulgarian, school={Karlsruher Institut für Technologie}, title={Bulgarian Speech Recognition and Multilingual Language Modeling}, year={2006}, supervisor={Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SA-Mircheva.pdf}, author={Mircheva, Aneliya} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_1299.php} @comment{Additional data: Institut für Logik, Komplexität und Deduktionssysteme, Lehrstuhl Prof. Waibel, Universität Karlsruhe} @studentresearchproject{honal2003correction, school={Karlsruher Institut für Technologie}, title={Correction of Disfluencies in Spontaneous Speech using a Noisy-Channel Approach}, year={2003}, supervisor={Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SA-Honal.pdf}, author={Honal, Matthias} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_1300.php} @comment{Additional data: Institut für Logik, Komplexität und Deduktionssysteme, Lehrstuhl Prof. Waibel, Universität Karlsruhe} @studentresearchproject{stüker2002automatic, school={Karlsruher Institut für Technologie}, title={Automatic Generation of Dictionaries - for New, Unseen Languages by Voting Phoneme Recognizers in Nine Different Languages}, year={2002}, supervisor={Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SA-Stueker.pdf}, author={Stüker, Sebastian} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_1301.php} @comment{Additional data: Institut für Logik, Komplexität und Deduktionssysteme, Lehrstuhl Prof. Waibel, Universität Karlsruhe} @studentresearchproject{wolff1999adaption, school={Karlsruher Institut für Technologie}, title={Adaption von Kontextentscheidungsbäumen auf neue Sprachen}, year={1999}, supervisor={Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SA-wolff.ps.gz}, author={Wolff, Roald} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_1304.php} @comment{Additional data: Institut für Logik, Komplexität und Deduktionssysteme, Lehrstuhl Prof. Waibel, Universität Karlsruhe} @studentresearchproject{raschke1998automatische, school={Karlsruher Institut für Technologie}, title={Automatische Generierung eines Aussprachewörterbuches und Initialisierung eines Erkenners für die kroatische Sprache}, year={1998}, supervisor={Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SA-raschke.ps.gz}, author={Raschke, Stefan} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_1303.php} @comment{Additional data: Institut für Logik, Komplexität und Deduktionssysteme, Lehrstuhl Prof. Waibel, Universität Karlsruhe} @studentresearchproject{reichert1998lautschriftumsetzung, school={Karlsruher Institut für Technologie}, year={1998}, title={Lautschriftumsetzung und Worttrennung der chinesischen Schriftsprache}, supervisor={Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SA-reichert.ps.gz http://www.csl.uni-bremen.de/cms/images/documents/publications/SA-reichert.pdf}, author={Reichert, Jürgen} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_1305.php} @comment{Additional data: Institut für Logik, Komplexität und Deduktionssysteme, Lehrstuhl Prof. Waibel, Universität Karlsruhe} @studentresearchproject{soltau1996sprachenidentifikation, school={Karlsruher Institut für Technologie}, year={1996}, title={Sprachenidentifikation mit neuronalen Netzen}, supervisor={Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SA-soltau.ps.gz}, author={Soltau, Hagen} } @comment{Old page: http://csl.anthropomatik.kit.edu/studienarbeiten_1306.php} @comment{Additional data: Institut für Logik, Komplexität und Deduktionssysteme, Lehrstuhl Prof. Waibel, Universität Karlsruhe} @studentresearchproject{schultz1994akustische, school={Karlsruher Institut für Technologie}, title={Akustische Modellierung sprachlicher und nichtsprachlicher Geräusche}, year={1994}, supervisor={Rogina, Ivica}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_SA.pdf http://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_SA.ps.gz}, author={Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2778.php} @diplomathesis{he2014rlat, school={Karlsruher Institut für Technologie}, title={RLAT Light - An Enhanced Version for Novices of the Rapid Language Adaptation Toolkit}, year={2014}, supervisor={Schlippe, Tim and Vu, Ngoc Thang and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Diplomarbeit_QingyueHe.pdf}, author={He, Qingyue} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2726.php} @diplomathesis{merz2014different, school={Karlsruher Institut für Technologie}, year={2014}, title={Different Methods for Efficient Semi-Automatic Pronunciation Generation}, supervisor={Schlippe, Tim and Schultz, Tanja}, author={Merz, Matthias} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2787.php} @diplomathesis{harnisch2014user, school={Karlsruher Institut für Technologie}, title={User Simulation in Cognitive Dialog Systems: An Application of the Multiple Resource Model}, year={2014}, supervisor={Putze, Felix and Schultz, Tanja}, author={Harnisch, Christian} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2840.php} @diplomathesis{rapp2014applying, school={Karlsruher Institut für Technologie}, title={Applying Linear Signal Transformation Techniques to Improve BCI Robustness}, year={2014}, supervisor={Heger, Dominik}, author={Rapp, Hannes} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2366.php} @diplomathesis{ikkert2013implementierung, school={Karlsruher Institut für Technologie}, title={Implementierung und Evaluation eines Large Margin Estimation Algorithmus für HMMs š}, year={2013}, supervisor={Wand, Michael and Vu, Thang and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/DA_MichaelIkkert.pdf}, author={Ikkert, Michael} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2368.php} @diplomathesis{johner2013erkennung, school={Karlsruher Institut für Technologie}, title={Erkennung prosodischer Merkmale durch EMG-basierte Klassifikation der Gesichtsmuskulatur}, year={2013}, supervisor={Janke, Matthias and Wand, Michael and Schultz, Tanja}, author={Johner, Christian} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2825.php} @diplomathesis{wellenbrock2013copulas, school={Karlsruher Institut für Technologie}, title={Copulas für die Merkmalauswahl}, year={2013}, supervisor={Heger, Dominic and Herff, Christian}, author={Wellenbrock, Christian} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2788.php} @diplomathesis{hesslinger2013hybrid, school={Karlsruher Institut für Technologie}, title={Hybrid NIRS-EEG based classification of auditory and visual perception processes}, year={2013}, supervisor={Putze, Felix and Schultz, Tanja}, author={Hesslinger, Sebastian} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2425.php} @diplomathesis{gren2013unsupervised, school={Karlsruher Institut für Technologie}, year={2013}, title={Unsupervised Language Model Adaptation for Automatic Speech Recognition of Broadcast News Using Web 2.0}, supervisor={Schlippe, Tim and Vu, Ngoc Thang and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/DA_LukaszGren.pdf}, author={Gren, Lukasz} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2790.php} @diplomathesis{wei2012experimentelle, school={Karlsruher Institut für Technologie}, title={Experimentelle Induktion und biosignalbasierte Erkennung Positiver und Negativer Stimmungen beim Autofahren}, year={2012}, supervisor={Putze, Felix and Heger, Dominic and Schultz, Tanja}, author={Wei, Ying} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2791.php} @diplomathesis{engelmann2012untersuchung, school={Karlsruher Institut für Technologie}, year={2012}, title={Untersuchung des Zusammenhangs von EEG basierten ereigniskorrelierten Potentialen und physischer und kognitiver Fitness bei jungen Studierenden}, supervisor={Putze, Felix and Heger, Dominic and Schultz, Tanja}, author={Engelmann, Jeremias} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_1265.php} @diplomathesis{sitto2011developing, school={Karlsruher Institut für Technologie}, year={2011}, title={Developing a Human Motion Recognition System by Applying Automatic Segmentation and Model Transfer}, supervisor={Gehrig, Dirk and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/DA_Sandro_Sitto.pdf}, author={Sitto, Sandro} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2480.php} @diplomathesis{mihaylova2011lexical, school={Karlsruher Institut für Technologie}, title={Lexical and Acoustic Adaptation for Multiple Non-Native English Accents}, year={2011}, supervisor={Schlippe, Tim and Vu, Ngoc Thang and Telaar, Dominic and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/DA_ZlatkaMihaylova.pdf}, author={Mihaylova, Zlatka} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_1624.php} @diplomathesis{herff2011speech, school={Karlsruher Institut für Technologie}, year={2011}, title={Speech Related Activations in the Brain: Differentiating between Speaking Modes with fNIRS}, supervisor={Putze, Felix and Heger, Dominic and Schultz, Tanja}, author={Herff, Christian} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2793.php} @diplomathesis{pröpper2011adaption, school={Karlsruher Institut für Technologie}, title={Adaption of cognitive models to dynamically changing mental workload}, year={2011}, supervisor={Putze, Felix and Schultz, Tanja}, author={Pröpper, Robert} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2046.php} @diplomathesis{gebhardt2011speech, school={Karlsruher Institut für Technologie}, year={2011}, title={Speech Recognition on English-Mandarin Code-Switching Data using Factored Language Models - with Port-of-Speech Tags, Language ID and Code-Switch Point Probability as Factors}, supervisor={Schlippe, Tim and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/DA_JanGebhardt.pdf}, author={Gebhardt, Jan} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2792.php} @diplomathesis{reich2011a, school={Karlsruher Institut für Technologie}, year={2011}, title={A Real-Time Speech Command Detector for a Smart Control Room}, supervisor={Putze, Felix and Heger, Dominic and Schultz, Tanja}, author={Reich, Daniel} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2794.php} @diplomathesis{jarvis2011multimodal, school={Karlsruher Institut für Technologie}, title={Multimodal Person Independent Recognition of Driver Mental Workload}, year={2011}, supervisor={Putze, Felix and Schultz, Tanja}, author={Jarvis, Jan-Philipp} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2114.php} @diplomathesis{kraus2011cross, school={Karlsruher Institut für Technologie}, year={2011}, title={Cross-Language Bootstrapping based on completely Unsupervised Training}, supervisor={Vu, Ngoc Thang and Schultz, Tanja}, author={Kraus, Franziska} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2839.php} @diplomathesis{jungkurth2011design, school={Karlsruher Institut für Technologie}, title={Design and Implemantation of a Motor Imagery based Brain-Computer Interface}, year={2011}, supervisor={Heger, Dominik}, author={Jungkurth, Henning} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2048.php} @diplomathesis{blaicher2011smt, school={Karlsruher Institut für Technologie}, title={SMT-based Text Generation for Code-Switching Language Models}, year={2011}, supervisor={Schlippe, Tim and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/DA_FabianBlaicher.pdf}, author={Blaicher, Fabian} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_1266.php} @diplomathesis{janke2010spektrale, school={Karlsruher Institut für Technologie}, title={Spektrale Methoden zur EMG-basierten Erkennung lautloser Sprache}, year={2010}, supervisor={Wand, Michael and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/DA-Janke.pdf}, author={Janke, Matthias} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_1268.php} @diplomathesis{pruzinec2010facial, school={Karlsruher Institut für Technologie}, title={Facial Expression Recognition using Surface Electromyography}, year={2010}, supervisor={Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/DA-Pruzinec.pdf}, author={Pruzinec, Martin} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_1267.php} @diplomathesis{feng2010initialization, school={Karlsruher Institut für Technologie}, title={Initialization Methods for an EMG-based Silent Speech Recognizer}, year={2010}, supervisor={Wand, Michael and Schultz, Tanja}, author={Feng, Gu} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2069.php} @diplomathesis{telaar2009multilingual, school={Karlsruher Institut für Technologie}, year={2009}, title={Multilingual Speech Recognition Using Bundled Phonetic Features}, supervisor={Schultz, Tanja}, author={Telaar, Dominic} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_1271.php} @diplomathesis{porbadnigk2009predicting, school={Karlsruher Institut für Technologie}, year={2009}, title={Predicting the BOLD Response: A Computational Model of Humans Solving an Arithmetic Task}, supervisor={Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/DA_Porbadnigk_03.pdf}, author={Porbadnigk, Anne} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2067.php} @diplomathesis{zipperle2009automatische, school={Karlsruher Institut für Technologie}, year={2009}, title={Automatische inhaltsbasierte Klassifikation elektronischer Musik}, supervisor={Schultz, Tanja}, author={Zipperle, Christoph} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2066.php} @diplomathesis{vasilec2009geometrischer, school={Karlsruher Institut für Technologie}, year={2009}, title={Geometrischer Modellabgleich für die bildbasierte Formalauswertung}, supervisor={Schultz, Tanja}, author={Vasilec, Tsoncho} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_1270.php} @diplomathesis{wielatt2009entwicklung, school={Karlsruher Institut für Technologie}, year={2009}, title={Entwicklung eines Werkzeuges zur Echtzeitvisualisierung von Biosignalen}, supervisor={Wand, Michael and Fischer, Andreas and Schultz, Tanja and Schwameder, Hermann}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ZA_Thomas_Wielatt.pdf}, author={Wielatt, Thomas} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_1272.php} @diplomathesis{könig2009systeme, school={Karlsruher Institut für Technologie}, title={Systeme und Methoden zur Erfassung der persönlichen Fitness}, year={2009}, supervisor={Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/DA_Koenig_SystemeMethodenPersFitness.pdf}, author={König, Nils} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2068.php} @diplomathesis{burgmer2009detecting, school={Karlsruher Institut für Technologie}, year={2009}, title={Detecting Code-Switch Events Based on Textual Features}, supervisor={Schultz, Tanja}, author={Burgmer, Christoph} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2796.php} @diplomathesis{heger2009towards, school={Karlsruher Institut für Technologie}, title={Towards Automatic Recognition of Personality for Human-Machine Interaction}, year={2009}, supervisor={Putze, Felix and Schultz, Tanja}, author={Heger, Dominic} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_1269.php} @diplomathesis{amma2009airwriting, school={Karlsruher Institut für Technologie}, title={Airwriting Recognition using Wearable Motion Sensors}, year={2009}, supervisor={Gehrig, Dirk and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/DA_Amma.pdf}, author={Amma, Christoph} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2065.php} @diplomathesis{stoimenov2009static, school={Karlsruher Institut für Technologie}, year={2009}, title={Static Search Space Modeling for Speech Recognition}, supervisor={Schultz, Tanja}, author={Stoimenov, Emilian} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_2045.php} @diplomathesis{vu2009entwicklung, school={Karlsruher Institut für Technologie}, year={2009}, title={Entwicklung eines vietnamesischen Spracherkennungssysems für große Vokabulare}, supervisor={Schultz, Tanja and Schlippe, Tim}, author={Vu, Ngoc Thang} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_1274.php} @diplomathesis{dahlmeier2008investigations, school={Karlsruher Institut für Technologie}, title={Investigations into the Use of Preposition Sense in Semantic Argument Classification}, year={2008}, supervisor={Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/DA-DanielDahlmeier.pdf}, author={Dahlmeier, Daniel} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_1273.php} @diplomathesis{schaaff2008eeg, school={Karlsruher Institut für Technologie}, title={EEG-based Emotion Recognition}, year={2008}, supervisor={Wand, Michael and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/DA-schaaff.pdf}, author={Schaaff, Kristina} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_1275.php} @comment{Additional data: Institut für Theoretische Informatik, Lehrstuhl Prof. Waibel, Universität Karlsruhe} @diplomathesis{wester2006unspoken, school={Karlsruher Institut für Technologie}, year={2006}, title={Unspoken Speech - Speech Recognition based on Electroencephalography}, supervisor={Schultz, Tanja}, author={Wester, Marek} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_1276.php} @comment{Additional data: Institut für Theoretische Informatik, Lehrstuhl Prof. Waibel, Universität Karlsruhe} @diplomathesis{honal2005determining, school={Karlsruher Institut für Technologie}, year={2005}, title={Determining User State and Mental Task Demand from Electroencephalograpic Data}, supervisor={Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/DA-Honal.pdf}, author={Honal, Matthias} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_1277.php} @comment{Additional data: Institut für Theoretische Informatik, Lehrstuhl Prof. Waibel, Universität Karlsruhe} @diplomathesis{maier-hein2005speech, school={Karlsruher Institut für Technologie}, year={2005}, title={Speech Recognition using Surface Electromyography}, supervisor={Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/DA-MaierHein.pdf}, author={Maier-Hein, Lena} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_1278.php} @comment{Additional data: Institut für Theoretische Informatik, Lehrstuhl Prof. Waibel, Universität Karlsruhe} @diplomathesis{paulik2005machine, school={Karlsruher Institut für Technologie}, title={Machine Translation Enhanced Automatic Speech Recognition}, year={2005}, supervisor={Fügen, Christian and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/DA-Paulik.pdf}, author={Paulik, Matthias} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_1280.php} @comment{Additional data: Institut für Logik, Komplexität und Deduktionssysteme, Lehrstuhl Prof. Waibel, Universität Karlsruhe} @diplomathesis{stüker2003multilingual, school={Karlsruher Institut für Technologie}, title={Multilingual Articulatory Features}, year={2003}, supervisor={Metze, Florian and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/DA-stueker.pdf}, author={Stüker, Sebastian} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_1281.php} @comment{Additional data: Institut für Logik, Komplexität und Deduktionssysteme, Lehrstuhl Prof. Waibel, Universität Karlsruhe} @diplomathesis{abu-alwan2000arabic, school={Karlsruher Institut für Technologie}, title={Arabic Speech Recognition}, year={2000}, supervisor={Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/DA-raschke.ps.gz}, author={Abu-Alwan, Jamal} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_1282.php} @comment{Additional data: Institut für Logik, Komplexität und Deduktionssysteme, Lehrstuhl Prof. Waibel, Universität Karlsruhe} @diplomathesis{kiecza1999datengetriebene, school={Karlsruher Institut für Technologie}, year={1999}, title={Datengetriebene Bestimmung von Wörterbucheinheiten für koreanische Spracherkennung auf großen Wortschätzen (Data-driven determination of appropriate dictionary units for Korean LVCSR)}, supervisor={Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/DA-kiecza.ps.gz}, author={Kiecza, Daniel} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_1283.php} @comment{Additional data: Institut für Logik, Komplexität und Deduktionssysteme, Lehrstuhl Prof. Waibel, Universität Karlsruhe} @diplomathesis{reichert1998spracherkennung, school={Karlsruher Institut für Technologie}, title={Spracherkennung im Chinesischen}, year={1998}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/DA-reichert.ps.gz}, author={Reichert, Jürgen} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_1284.php} @comment{Additional data: Institut für Logik, Komplexität und Deduktionssysteme, Lehrstuhl Prof. Waibel, Universität Karlsruhe} @diplomathesis{Çarki1998entwicklung, school={Karlsruher Institut für Technologie}, year={1998}, title={Entwicklung eines türkischen Spracherkennungssystems für große Vokabulare}, supervisor={Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/DA-carki.ps.gz}, author={Çarki, Kenan} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_1285.php} @comment{Additional data: Institut für Logik, Komplexität und Deduktionssysteme, Lehrstuhl Prof. Waibel, Universität Karlsruhe} @diplomathesis{soltau1997erkennung, school={Karlsruher Institut für Technologie}, title={Erkennung von Musikstilen}, year={1997}, supervisor={Schultz, Tanja}, author={Soltau, Hagen} } @comment{Old page: http://csl.anthropomatik.kit.edu/diplomarbeiten_1286.php} @comment{Additional data: Institut für Logik, Komplexität und Deduktionssysteme, Lehrstuhl Prof. Waibel, Universität Karlsruhe} @diplomathesis{schultz1995identifizierung, school={Karlsruher Institut für Technologie}, title={Identifizierung von Sprachen -Exemplarisch aufgezeigt am Beispiel der Sprachen Deutsch, Englisch und Spanisch}, year={1995}, supervisor={Rogina, Ivica}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_DA.pdf http://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_DA.ps.gz}, author={Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2919.php} @inproceedings{stahlberg2015cross, note={ICASSP 2015}, title={Cross-lingual Lexical Language Discovery from Audio Data Using Multiple Translations}, year={2015}, booktitle={The 40th International Conference on Acoustics, Speech, and Signal Processing, Brisbane, Australia}, author={Stahlberg, Felix and Schlippe, Tim and Vogel, Stephan and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2912.php} @inproceedings{georgi2015recognizing, note={BIOSIGNALS 2015}, year={2015}, title={Recognizing Hand and Finger Gestures with IMU based Motion and EMG based Muscle Activity Sensing}, booktitle={International Conference on Bio-inspired Systems and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/GeorgiAmmaSchultz_RecognizingHandAndFingerGesturesWithIMUBasedMotionAndEMGBasedMuscleActivitySensing.pdf}, author={Georgi, Marcus and Amma, Christoph and Schultz, Tanja}, doi={10.5220/0005276900990108}, pages={99-108} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2904.php} @inproceedings{srisuwan2014enhancement, title={Enhancement of EMG-based Thai Number Words Classification using Frame-based Time Domain Feature with Stacking Filter}, year={2014}, booktitle={Proceedings of 2014 APSIPA Annual Summit and Conference}, abstract={In order to overcome a problem existing in a classical automatic speech recognition (e.g. ambient noise and loss of privacy), Electromyography (EMG) from speech production muscles was used in place of a human speech signal. We aim to investigate the EMG speech recognition based on Thai language. The earlier work, we used five channels of the EMG from the facial and neck muscles to classify 11 Thai number words based on Neural Network Classification. 15 features in time domain and frequency domain were employed for feature extraction. We obtained an average accuracy rate of 89.45% for audible speech and 78.55% for silent speech. However, it needs to be enhanced to get the best result. This paper proposes to improve an accuracy rate of EMG-based Thai number words classification. The ten subjects uttered 11 words in both an audible and a silent speech while five channels of the EMG signal were captured. Frame-based time domain features with a stacking filter was performed for feature extraction stage. After that, LDA was used to lessen a dimension of the feature vector. Hidden Markov Model (HMM) was employed in classification stage. The results show that using above techniques of feature extraction, feature dimensionality reduction and classification can improve an average accuracy rate by 3% absolute for audible speech when were compared to earlier work. We achieved an average classification rate of 92.45% and 75.73% for audible and silent speech respectively.}, author={Srisuwan, Niyawadee Jib and Limsakul, Chusak and Phukpattaranont, Pornchai and Schultz, Tanja and Wand, Michael and Janke, Matthias} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2879.php} @inproceedings{wand2014pattern, year={2014}, title={Pattern Learning with Deep Neural Networks in EMG-based Speech Recognition}, note={EMBC 2014}, booktitle={36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Wand_EMBC14_DNN_EMGSpeechRecognition.pdf}, author={Wand, Michael and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2861.php} @inproceedings{wand2014towards, title={Towards Real-life Application of EMG-based Speech Recognition by using Unsupervised Adaptation}, year={2014}, note={Interspeech 2014}, booktitle={The 15th Annual Conference of the International Speech Communication Association, Singapore}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/WandSchultz_IS14_EMGSpeechRecognitionUnsupervisedAdaptation.pdf}, author={Wand, Michael and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2860.php} @inproceedings{wand2014the, year={2014}, title={The EMG-UKA Corpus for Electromyographic Speech Processing}, note={Interspeech 2014}, booktitle={The 15th Annual Conference of the International Speech Communication Association, Singapore}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/WandJankeSchultz_IS14_EMG-UKA-Corpus.pdf}, abstract={This article gives an overview of the EMG-UKA corpus, a corpus of electromyographic (EMG) recordings of articulatory activity enabling speech processing (in particular speech recognition and synthesis) based on EMG signals, with the purpose of building Silent Speech interfaces. Data is available in multiple speaking modes, namely audibly spoken, whispered, and silently articulated speech. Besides the EMG data, synchronous acoustic data was additionally recorded to serve as a reference. The corpus comprises 63 recorded sessions from 8 speakers, the total amount of data is 7:32 hours. A trial subset, consisting of 1:52 hours of data, is freely available for download.}, author={Wand, Michael and Janke, Matthias and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2858.php} @inproceedings{zahner2014conversion, note={Interspeech 2014}, year={2014}, title={Conversion from Facial Myoelectric Signals to Speech: A Unit Selection Approach}, booktitle={The 15th Annual Conference of the International Speech Communication Association, Singapore}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ZahnerJankeWandSchultz_IS14_MyoelectricSignalsUnitSelection.pdf}, abstract={This paper reports on our recent research on surface electromyographic (EMG) speech synthesis: a direct conversion of the EMG signals of the articulatory muscle movements to the acoustic speech signal. In this work we introduce a unit selection approach which compares segments of the input EMG signal to a database of simultaneously recorded EMG/audio unit pairs and selects the best matching audio unit based on target and concatenation cost, which will be concatenated to synthesize an acoustic speech output. We show that this approach is feasible to generate a proper speech output from the input EMG signal. We evaluate different properties of the units and investigate what amount of data is necessary for an initial transformation. Prior work on EMG-to-speech conversion used a framebased approach from the voice conversion domain, which struggles with the generation of a natural $F_0$ contour. This problem may also be tackled by our unit selection approach.}, author={Zahner, Marlene and Janke, Matthias and Wand, Michael and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2856.php} @inproceedings{vu2014investigating, year={2014}, title={Investigating the Learning Effect of Multilingual Bottle-Neck Features for ASR}, note={Interspeech 2014}, booktitle={The 15th Annual Conference of the International Speech Communication Association, Singapore}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/354_Paper.pdf}, author={Vu, Ngoc Thang and Weiner, Jochen and Schultz, Tanja}, abstract={Deep neural networks (DNNs) have become state-of-the-art techniques of automatic speech recognition in the last few years. They can be used at the preprocessing level (Tandem or Bottle-Neck features) or at the acoustic model level (hybrid Hidden Markov Model/DNN). Moreover, they allow exploiting multilingual data to improve monolingual systems. This paper presents our investigation of the learning effect of neural networks in the context of multilingual Bottle-Neck features. For this, we perform a visual analysis of the output of the Bottle-Neck layer of a neural network using t-Distributed Stochastic Neighbor Embedding. Our results show that multilingual Bottle-Neck features seem to learn phoneme characteristics, such as the F1 and F2 formants which characterize different vowels, and other articulatory features, such as fricatives and nasals which characterize consonants. Furthermore, they seem to normalize language dependent variations and transfer the learned representation to unseen languages.} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2854.php} @inproceedings{vu2014improving, year={2014}, title={Improving ASR Performance On Non-native Speech Using Multilingual and Crosslingual Information}, note={Interspeech 2014}, booktitle={The 15th Annual Conference of the International Speech Communication Association, Singapore}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/vu_interspeech2014_final.pdf}, author={Vu, Ngoc Thang and Wang, Yuanfan and Klose, Marten and Mihaylova, Zlatka and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2828.php} @inproceedings{adel2014combining, note={Interspeech 2014}, year={2014}, title={Combining Recurrent Neural Networks and Factored Language Models During Decoding of Code-Switching Speech}, booktitle={The 15th Annual Conference of the International Speech Communication Association, Singapore}, author={Adel, Heike and Telaar, Dominic and Vu, Ngoc Thang and Kirchhoff, Katrin and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2827.php} @inproceedings{adel2014comparing, title={Comparing Approaches to Convert Recurrent Neural Networks into Backoff Language Models For Efficient Decoding}, year={2014}, note={Interspeech 2014}, booktitle={The 15th Annual Conference of the International Speech Communication Association, Singapore}, author={Adel, Heike and Kirchhoff, Katrin and Vu, Ngoc Thang and Telaar, Dominic and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2776.php} @inproceedings{schlippe2014methods, note={Interspeech 2014}, year={2014}, title={Methods for Efficient Semi-Automatic Pronunciation Dictionary Bootstrapping}, booktitle={The 15th Annual Conference of the International Speech Communication Association, Singapore}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Interspeech2014-Schlippe_SemiAutomaticDictBootstrapping.pdf}, author={Schlippe, Tim and Merz, Matthias and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2775.php} @inproceedings{telaar2014biokit, title={BioKIT - Real-time Decoder For Biosignal Processing}, year={2014}, note={Interspeech 2014}, booktitle={The 15th Annual Conference of the International Speech Communication Association, Singapore}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/TelaarEtAl_IS14_BioKIT.pdf}, abstract={We introduce BioKIT, a new Hidden Markov Model based toolkit to preprocess, model and interpret biosignals such as speech, motion, muscle and brain activities. The focus of this toolkit is to enable researchers from various communities to pursue their experiments and integrate real-time biosignal interpretation into their applications. BioKIT boosts a flexible two-layer structure with a modular C++ core that interfaces with a Python scripting layer, to facilitate development of new applications. BioKIT employs sequence-level parallelization and memory sharing across threads. Additionally, a fully integrated error blaming component facilitates in-depth analysis. A generic terminology keeps the barrier to entry for researchers from multiple fields to a minimum. We describe our online-capable dynamic decoder and report on initial experiments on three different tasks. The presented speech recognition experiments employ Kaldi trained deep neural networks with the results set in relation to the real time factor needed to obtain them.}, author={Telaar, Dominic and Wand, Michael and Gehrig, Dirk and Putze, Felix and Amma, Christoph and Heger, Dominic and Vu, Ngoc Thang and Erhardt, Mark and Schlippe, Tim and Janke, Matthias and Herff, Christian and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2763.php} @INPROCEEDINGS{6944010, author={Heger, D. and Herff, C. and Schultz, T.}, booktitle={Engineering in Medicine and Biology Society (EMBC), 2014 36th Annual International Conference of the IEEE}, title={Combining feature extraction and classification for fNIRS BCIs by regularized least squares optimization}, year={2014}, pages={2012-2015}, abstract={In this paper, we show that multiple operations of the typical pattern recognition chain of an fNIRS-based BCI, including feature extraction and classification, can be unified by solving a convex optimization problem. We formulate a regularized least squares problem that learns a single affine transformation of raw HbO2 and HbR signals. We show that this transformation can achieve competitive results in an fNIRS BCI classification task, as it significantly improves recognition of different levels of workload over previously published results on a publicly available n-back data set. Furthermore, we visualize the learned models and analyze their spatio-temporal characteristics.}, keywords={affine transforms;biochemistry;bioelectric potentials;brain-computer interfaces;electroencephalography;feature extraction;feature selection;infrared spectra;least mean squares methods;medical signal processing;molecular biophysics;optimisation;oxygen;proteins;spatiotemporal phenomena;O2;affine transformation;convex optimization problem;deoxygenated hemoglobin signals;fNIRS BCI classification task;feature classification;feature extraction;functional near-infrared spectroscopy;pattern recognition chain;regularized least squares optimization;spatiotemporal characteristic analysis;Analytical models;Brain models;Data models;Feature extraction;Optimization;Predictive models}, doi={10.1109/EMBC.2014.6944010}, ISSN={1557-170X}, month={Aug},} @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2757.php} @inproceedings{putze2013profiling, title={Profiling Arousal in Response to Complex Stimuli using Biosignals}, year={2013}, booktitle={International Conference on Bio-inspired Systems and Signal Processing 2013}, author={Putze, Felix and Heger, Dominic and Müller, M. and Kajic, Ivana and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2756.php} @inproceedings{putze2013session, year={2013}, title={Session-independent EEG-based Workload Recognition}, booktitle={International Conference on Bio-inspired Systems and Signal Processing 2013}, author={Putze, Felix and Müller, M. and Heger, Dominic and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2755.php} @INPROCEEDINGS{6853962, author={Heger, D. and Terziyska, E. and Schultz, T.}, booktitle={Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on}, title={Connectivity based feature-level filtering for single-trial EEG BCIs}, year={2014}, pages={2064-2068}, abstract={EEG-based Brain Computer interfaces (BCIs) often rely on power spectral density features to represent relevant aspects of brain activity. The information flow within human brain networks and the corresponding connectivity patterns may contain useful information to improve BCI performance, however they are typically not leveraged in current systems. In this paper, analyzes of information flow between independent sources of brain activity have been incorporated into the feature extraction stage of a BCI. For this purpose, connectivity measures based on multivariate autoregressive models have been estimated and are applied as filters to power spectral density based features. Two publicly available data sets have been used to evaluate the proposed feature extraction method: a two-back task and a motor imagery task. The results demonstrate significant performance improvements of the proposed method over band-power features and indicate that connectivity in brain networks can be used as powerful feature-level filters for BCIs.}, keywords={autoregressive processes;brain;brain-computer interfaces;electroencephalography;feature extraction;medical signal processing;EEG-based brain computer interfaces;band-power feature;brain activity;connectivity measure;connectivity pattern;electroencephalography;feature extraction method;feature-level filtering;human brain network;information flow;motor imagery task;multivariate autoregressive model;power spectral density feature;publicly available data set;single-trial EEG BCIs;two-back task;Brain models;Electroencephalography;Feature extraction;Time series analysis;Transfer functions;Connectivity;Granger causality;brain-computer interfaces;direct directed transfer function;electroencephalography}, doi={10.1109/ICASSP.2014.6853962}, month={May},} @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2722.php} @inproceedings{schultz2014globalphone, title={GlobalPhone: Pronunciation Dictionaries in 20 Languages}, year={2014}, note={LREC 2014}, booktitle={The 9th edition of the Language Resources and Evaluation Conference, Reykjavik, Iceland}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/LREC2014-SchultzSchlippe_GlobalPhoneDicts.pdf}, author={Schultz, Tanja and Schlippe, Tim} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2721.php} @inproceedings{schlippe2014combining, note={SLTU 2014}, title={Combining Grapheme-to-Phoneme Converter Outputs for Enhanced Pronunciation Generation in Low-Resource Scenarios}, year={2014}, booktitle={The 4th Workshop on Spoken Language Technologies for Under-resourced Languages, St. Petersburg, Russia}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SLTU2014-Schlippe_G2PConverterOutputCombination.pdf}, author={Schlippe, Tim and Quaschningk, Wolf and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2720.php} @inproceedings{leidig2014automatic, title={Automatic Detection of Anglicisms for the Pronunciation Dictionary Generation: A Case Study on our German IT Corpus}, year={2014}, note={SLTU 2014}, booktitle={The 4th Workshop on Spoken Language Technologies for Under-resourced Languages, St. Petersburg, Russia}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SLTU2014-LeidigSchlippe_AnglicismDetection.pdf}, author={Leidig, Sebastian and Schlippe, Tim and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2719.php} @inproceedings{stahlberg2014towards, year={2014}, title={Towards Automatic Speech Recognition without Pronunciation Dictionary, Transcribed Speech and Text Resources in the Target Language using Cross-Lingual Word-to-Phoneme Alignment}, note={SLTU 2014}, booktitle={The 4th Workshop on Spoken Language Technologies for Under-resourced Languages, St. Petersburg, Russia}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SLTU2014-StahlbergSchlippe_ASRWithoutResources.pdf}, author={Stahlberg, Felix and Schlippe, Tim and Vogel, Stephan and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2718.php} @inproceedings{adel2014features, title={Features for Factored Language Models for Code-Switching Speech}, year={2014}, note={SLTU 2014}, booktitle={The 4th Workshop on Spoken Language Technologies for Under-resourced Languages, St. Petersburg, Russia}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/2768.php}, author={Adel, Heike and Kirchhoff, Kartin and Telaar, Dominic and Vu, Ngoc Thang and Schlippe, Tim and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2682.php} @inproceedings{janke2014fundamental, year={2014}, title={Fundamental Frequency Generation for Whisper-to-Audible Speech Conversion}, note={ICASSP 2014}, booktitle={The 39th International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Janke_ICASSP14_F0GenerationWhisper.pdf}, abstract={In this work, we address the issues involved in whisper-to-audible speech conversion. Spectral mapping techniques using Gaussian mixture models or Artificial Neural Networks borrowed from voice conversion have been applied to transform whisper spectral features to normally phonated audible speech. However, the modeling and generation of fundamental frequency ($F_0$) and its contour in the converted speech is a major issue. Whispered speech does not contain explicit voicing characteristics and hence it is hard to derive a suitable $F_0$, making it difficult to generate a natural prosody after conversion. Our work addresses the $F_0$ modeling in whisper-to-speech conversion. We show that $F_0$ contours can be derived from the mapped spectral vectors, which can be used for the synthesis of a speech signal. We also present a hybrid unit selection approach for whisper-to-speech conversion. Unit selection is performed on the spectral vectors, where $F_0$ and its contour can be obtained as a byproduct without any additional modeling.}, author={Janke, Matthias and Prahallad, Kishore and Wand, Michael and Heistermann, Till and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2678.php} @inproceedings{wand2014compensation, title={Compensation of Recording Position Shifts for a Myoelectric Silent Speech Recognizer}, year={2014}, note={ICASSP 2014}, booktitle={The 39th International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Wand_ICASSP14_EMGArrayShift.pdf}, abstract={A myoelectric Silent Speech Recognizer is a system which recognizes speech by capturing the electrical activity of the human articulatory muscles, thus enabling the user to communicate silently. We recently devised a recording setup based on electrode arrays with multiple measuring points. In this study we show that this allows to compensate for shifts of the recording position, which happen when the array is removed and reattached between system training and application. We present a method which determines the amount of recording position shift; compensation is performed by linear interpolation. We evaluate our method by running recognition experiments across recording sessions and obtain a Word Error Rate improvement of 14.3% relative on the development set and 12.9% relative on the evaluation set, compared to using classical session adaptation.}, author={Wand, Michael and Schulte, Christopher and Janke, Matthias and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2658.php} @inproceedings{heistermann2014spatial, title={Spatial Artifact Detection for Multi-Channel EMG-Based Speech Recognition}, year={2014}, note={BIOSIGNALS 2014}, booktitle={7th International Conference on Bio-inspired Systems and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Heistermann_et_al_BS2014_SpatialArtifactDetection.pdf}, abstract={We introduce a spatial artifact detection method for a surface electromyography (EMG) based speech recognition system. The EMG signals are recorded using grid-shaped electrode arrays affixed to the speakers face. Continuous speech recognition is performed on the basis of these signals. As the EMG data are high-dimensional, Independent Component Analysis (ICA) can be applied to separate artifact components from the content-bearing signal. The proposed artifact detection method classifies the ICA components by their spatial shape, which is analyzed using the spectra of the spatial patterns of the independent components. Components identified as artifacts can then be removed. Our artifact detection method reduces the word error rates (WER) of the recognizer significantly. We observe a slight advantage in terms of WER over the temporal signal based artifact detection method by (Wand et al., 2013a).}, author={Heistermann, Till and Janke, Matthias and Wand, Michael and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2668.php} @inproceedings{putze2013reliable, year={2013}, title={Reliable Subject-Adapted Recognition of EEG Error Potentials Using Limited Calibration Data}, booktitle={International IEEE EMBS Neural Engineering Conference 2013, San Diego, USA}, author={Putze, Felix and Heger, Dominic and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2666.php} @inproceedings{Putze:2013:LUA:2449396.2449415, author = {Putze, Felix and Hild, Jutta and K\"{a}rgel, Rainer and Herff, Christian and Redmann, Alexander and Beyerer, J\"{u}rgen and Schultz, Tanja}, title = {Locating User Attention Using Eye Tracking and EEG for Spatio-temporal Event Selection}, booktitle = {Proceedings of the 2013 International Conference on Intelligent User Interfaces}, series = {IUI '13}, year = {2013}, isbn = {978-1-4503-1965-2}, location = {Santa Monica, California, USA}, pages = {129--136}, numpages = {8}, url = {http://doi.acm.org/10.1145/2449396.2449415}, doi = {10.1145/2449396.2449415}, acmid = {2449415}, publisher = {ACM}, address = {New York, NY, USA}, keywords = {eeg, event detection, expert video analysis, eye tracking}, } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2524.php} @INPROCEEDINGS{6681548, author={Heger, D. and Mutter, R. and Herff, C. and Putze, F. and Schultz, T.}, booktitle={Affective Computing and Intelligent Interaction (ACII), 2013 Humaine Association Conference on}, title={Continuous Recognition of Affective States by Functional Near Infrared Spectroscopy Signals}, year={2013}, pages={832-837}, abstract={Functional near infrared spectroscopy (fNIRS) is becoming more and more popular as an innovative imaging modality for brain computer interfaces. A continuous (i.e. asynchronous) affective state monitoring system using fNIRS signals would be highly relevant for numerous disciplines, including adaptive user interfaces, entertainment, biofeedback, and medical applications. However, only stimulus-locked emotion recognition systems have been proposed by now. fNRIS signals of eight subjects at eight prefrontal locations have been recorded in response to three different classes of affect induction by emotional audio-visual stimuli and a neutral class. Our system evaluates short windows of five seconds length to continuously recognize affective states. We analyze hemodynamic responses, present a careful evaluation of binary classification tasks and investigate classification accuracies over the time.}, keywords={audio-visual systems;haemodynamics;infrared spectra;pattern classification;physiology;psychology;signal classification;adaptive user interfaces;affect induction;asynchronous affective state monitoring system;binary classification task accuracies;biofeedback application;brain computer interface;continuous affective state recognition;emotional audio-visual stimuli;entertainment application;fNRIS signal recording;functional near infrared spectroscopy signals;hemodynamic response analysis;imaging modality;medical application;neutral class;prefrontal locations;short-window evaluation;stimulus-locked emotion recognition systems;Accuracy;Detectors;Emotion recognition;Feature extraction;Hemodynamics;Monitoring;Training data;affective states;asynchronous;continuous recognition;emotion recognition;fNIRS;functional Near Infrared Spectroscopy}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/acii13_paper.pdf}, doi={10.1109/ACII.2013.156}, ISSN={2156-8103}, month={Sept},} @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2510.php} @inproceedings{nallasamy2012active, year={2012}, title={Active Learning for Accent Adaptation in Automatic Speech Recognition}, note={SLT 2012}, booktitle={The Fourth IEEE Workshop on Spoken Language Technology}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SLT2012_UdhayNallasamy.pdf}, author={Nallasamy, Udhyakumar and Metze, Florian and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2504.php} @inproceedings{amma2013compressed, note={UbiComp 2013}, year={2013}, title={Compressed Signal Representation for Inertial Sensor Signals}, booktitle={2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing}, author={Amma, Christoph and Volk, Hannes and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2498.php} @inproceedings{adel2013combination, title={Combination of Recurrent Neural Networks and Factored Language Models for Code-Switching Language Modeling}, year={2013}, note={ACL 2013}, booktitle={The 51st Annual Meeting of the Association for Computational Linguistics, Sofia, Bulgaria}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Adel_Vu_ACL_2013.pdf}, author={Adel, Heike and Vu, Ngoc Thang and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2496.php} @inproceedings{premkumar2013experiments, note={Interspeech 2013}, year={2013}, title={Experiments towards a better LVCSR System for Tamil}, booktitle={14th Annual Conference of the International Speech Communication Association, Lyon, France}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/tamil_interspeech2013.pdf}, author={Premkumar, Melvin Jose Johnson and Vu, Ngoc Thang and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2487.php} @inproceedings{vu2013an, title={An Investigation of Code-Switching Attitude Dependent Language Modeling}, year={2013}, note={SLSP 2013}, booktitle={The 1st International Conference on Statistical Language and Speech Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/vu_adel_slsp2013.pdf}, author={Vu, Ngoc Thang and Adel, Heike and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2485.php} @inproceedings{vu2013multilingual, note={Interspeech 2013}, title={Multilingual Multilayer Perceptron For Rapid Language Adaptation Between and Across Language Families}, year={2013}, booktitle={14th Annual Conference of the International Speech Communication Association, Lyon, France}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/vu_mlp_interspeech2013.pdf}, author={Vu, Ngoc Thang and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2423.php} @inproceedings{schlippe2013unsupervised, note={Interspeech 2013}, title={Unsupervised Language Model Adaptation for Automatic Speech Recognition of Broadcast News Using Web 2.0}, year={2013}, booktitle={14th Annual Conference of the International Speech Communication Association, Lyon, France}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Interspeech2013-Schlippe_LMAdaptationWeb2.0.pdf}, author={Schlippe, Tim and Gren, Lukasz and Vu, Ngoc Thang and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2371.php} @inproceedings{telaar2013accent, title={Accent- and Speaker-Specific Polyphone Decision Trees for Non-Native Speech Recognition}, year={2013}, booktitle={14th Annual Conference of the International Speech Communication Association, Lyon, France}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/telaarInterspeech2013.pdf}, author={Telaar, Dominic and Fuhs, Mark C.} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2285.php} @inproceedings{wand2013artifact, year={2013}, title={Artifact Removal Algorithm for an EMG-based Silent Speech Interface}, note={EMBC 2013}, booktitle={International Conference of the IEEE Engineering in Medicine and Biology Society, Osaka, Japan}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/WandSchultz_EMBC2013.pdf}, abstract={An electromygraphic (EMG) Silent Speech Interface is a system which recognizes speech by capturing the electric potentials of the human articulatory muscles, thus enabling the user to communicate silently. This study deals with improving the EMG signal quality by removing artifacts: The EMG signals are captured by electrode arrays with multiple measuring points. On the resulting high-dimensional signal, Independent Component Analysis is performed, and artifact components are automatically detected and removed. This method reduces the Word Error Rate of the silent speech recognizer by 9.9% relative on a development corpus, and by 13.9% relative on an evaluation corpus.}, author={Wand, Michael and Himmelsbach, Adam and Heistermann, Till and Janke, Matthias and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2287.php} @INPROCEEDINGS{6610823, author={Heger, D. and Putze, F. and Herff, C. and Schultz, T.}, booktitle={Engineering in Medicine and Biology Society (EMBC), 2013 35th Annual International Conference of the IEEE}, title={Subject-to-subject transfer for CSP based BCIs: Feature space transformation and decision-level fusion}, year={2013}, pages={5614-5617}, abstract={Modern Brain Computer Interfaces (BCIs) usually require a calibration session to train a machine learning system before each usage. In general, such trained systems are highly specialized to the subject's characteristic activation patterns and cannot be used for other sessions or subjects. This paper presents a feature space transformation that transforms features generated using subject-specific spatial filters into a subject-independent feature space. The transformation can be estimated from little adaptation data of the subject. Furthermore, we combine three different Common Spatial Pattern based feature extraction approaches using decision-level fusion, which enables BCI use when little calibration data is available, but also outperformed the subject-dependent reference approaches for larger amounts of training data.}, keywords={brain-computer interfaces;calibration;feature extraction;learning (artificial intelligence);sensor fusion;spatial filters;brain computer interfaces;calibration;common spatial patterns;decision-level fusion;feature extraction;feature space transformation;machine learning system;subject-independent feature space;subject-specific spatial filters;subject-to-subject transfer;Brain-computer interfaces;Calibration;Electroencephalography;Feature extraction;Testing;Training;Transforms}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/EMBC13_2191_FI.pdf}, doi={10.1109/EMBC.2013.6610823}, ISSN={1557-170X}, month={July},} @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2283.php} @INPROCEEDINGS{6609962, author={Herff, C. and Heger, D. and Putze, F. and Hennrich, J. and Fortmann, O. and Schultz, T.}, booktitle={Engineering in Medicine and Biology Society (EMBC), 2013 35th Annual International Conference of the IEEE}, title={Classification of mental tasks in the prefrontal cortex using fNIRS}, year={2013}, pages={2160-2163}, abstract={Functional near infrared spectroscopy (fNIRS) is rapidly gaining interest in both the Neuroscience, as well as the Brain-Computer-Interface (BCI) community. Despite these efforts, most single-trial analysis of fNIRS data is focused on motor-imagery, or mental arithmetics. In this study, we investigate the suitability of different mental tasks, namely mental arithmetics, word generation and mental rotation for fNIRS based BCIs. We provide the first systematic comparison of classification accuracies achieved in a sample study. Data was collected from 10 subjects performing these three tasks. An optode template with 8 channels was chosen which covers the prefrontal cortex and only requires less than 3 minutes for setup. Two-class accuracies of up to 71% average across all subjects for mental arithmetics, 70% for word generation and 62% for mental rotation were achieved discriminating these tasks from a relax state. We thus lay the foundation for fNIRS based BCI using additional mental strategies than motor imagery and mental arithmetics. The tasks were chosen in a way that they might be used for user state monitoring, as well.}, keywords={arithmetic;biomedical equipment;brain-computer interfaces;cognition;feature extraction;fibre optic sensors;infrared spectroscopy;medical signal processing;neurophysiology;patient monitoring;signal classification;brain-computer interface;classification accuracy;fNIRS based BCI;fNIRS data single-trial analysis;functional near infrared spectroscopy;mental arithmetics;mental rotation;mental strategy;mental task classification;motor imagery;motor-imagery;neuroscience;optode template channel;prefrontal cortex;relax state;user state monitoring;word generation;Accuracy;Electroencephalography;Feature extraction;Hemodynamics;Neuroscience;Spectroscopy;Systematics}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/HerffSchultz_EMBC2013.pdf}, doi={10.1109/EMBC.2013.6609962}, ISSN={1557-170X}, month={July},} @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2280.php} @inproceedings{heger2013towards, title={Towards Biometric Person Identification using fNIRS}, year={2013}, booktitle={International BCI Meeting 2013, Asilomar, USA}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/heger_towards_biometric_BCI-meeting_2013_USletter.pdf}, author={Heger, Dominic and Herff, Christian and Putze, Felix and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2278.php} @inproceedings{herff2013self, title={Self-paced BCI with NIRS based on speech activity}, year={2013}, booktitle={International BCI Meeting 2013, Asilomar, USA}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/HerffSchultz_BCIMEETING2013.pdf}, author={Herff, Christian and Heger, Dominic and Putze, Felix and Guan, Cuntai and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2275.php} @inproceedings{stahlberg2013pronunciation, note={SLSP 2013}, title={Pronunciation Extraction from Phoneme Sequences through Cross-Lingual Word-to-Phoneme Alignment}, year={2013}, booktitle={The 1st International Conference on Statistical Language and Speech Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SLSP2013-StahlbergSchlippe_PronunciationExtraction.pdf}, author={Stahlberg, Felix and Schlippe, Tim and Vogel, Stephan and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2274.php} @inproceedings{schlippe2013rapid, note={ICASSP 2013}, title={Rapid Bootstrapping of a Ukrainian Large Vocabulary Continuous Speech Recognition System}, year={2013}, booktitle={The 38th International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ICASSP2013-Schlippe_UkrainianLVCSR.pdf}, author={Schlippe, Tim and Volovyk, Mykola and Yurchenko, Kateryna and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2273.php} @inproceedings{schultz2013globalphone, note={ICASSP 2013}, title={GlobalPhone: A Multilingual Text & Speech Database in 20 Languages}, year={2013}, booktitle={The 38th International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ICASSP2013-Schultz_GlobalPhone.pdf}, author={Schultz, Tanja and Vu, Ngoc Thang and Schlippe, Tim} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2272.php} @inproceedings{adel2013recurrent, year={2013}, title={Recurrent Neural Network Language Modeling for Code Switching Conversational Speech}, note={ICASSP 2013}, booktitle={The 38th International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ICASSP2013-Adel_NNLM4CS.pdf}, author={Adel, Heike and Vu, Ngoc Thang and Kraus, Franziska and Schlippe, Tim and Li, Haizhou and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2271.php} @inproceedings{schlippe2013statistical, year={2013}, title={Statistical Machine Translation based Text Normalization with Crowdsourcing}, note={ICASSP 2013}, booktitle={The 38th International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ICASSP2013-Schlippe_SMTTextNormalization.pdf}, author={Schlippe, Tim and Zhu, Chenfei and Lemcke, Daniel and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2262.php} @inproceedings{stahlberg2012word, title={Word Segmentation through Cross-Lingual Word-to-Phoneme Alignment}, year={2012}, note={SLT 2012}, booktitle={The Fourth IEEE Workshop on Spoken Language Technology}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SLT2012-StahlbergSchlippe_Model3P.pdf}, author={Stahlberg, Felix and Schlippe, Tim and Vogel, Stephan and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2200.php} @inproceedings{rebelo2013activity, title={Activity Recognition for an Intelligent Knee Orthosis}, year={2013}, note={BIOSIGNALS 2013}, booktitle={6th International Conference on Bio-inspired Systems and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/RebeloAmmaGamboaSchultz_Biosignals2013.pdf}, author={Rebelo, Diliana and Amma, Christoph and Gamboa, Hugo and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2190.php} @inproceedings{wand2013array, note={BIOSIGNALS 2013}, title={Array-based Electromyographic Silent Speech Interface}, year={2013}, booktitle={6th International Conference on Bio-inspired Systems and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/BS13_WandSchulteJankeSchultz_ArrayBasedEMGSSI.pdf}, abstract={An electromygraphic (EMG) Silent Speech Interface is a system which recognizes speech by capturing the electric potentials of the human articulatory muscles, thus enabling the user to communicate silently. This study is concerned with introducing an EMG recording system based on multi-channel electrode arrays. We first present our new system and introduce a method to deal with undertraining effects which emerge due to the high dimensionality of our EMG features. Second, we show that Independent Component Analysis improves the classification accuracy of the EMG array-based recognizer by up to 22.9% relative, which is a first example of an EMG signal processing method which is specifically enabled by our new array-based system. We evaluate our system on recordings of audible speech; achieving an optimal average word error rate of 10.9% with a training set of less than 10 minutes on a vocabulary of 108 words.}, author={Wand, Michael and Schulte, Christopher and Janke, Matthias and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2163.php} @inproceedings{amma2010emotionserkennung, title={Emotionserkennung auf der Basis von Gangmustern}, year={2010}, booktitle={Sportinformatik trifft Sporttechnologie, Tagung der dvs-Sektion Sportinformatik in Kooperation mit der Deutschen Interdisziplinären Vereinigung für Sporttechnologie}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Sportinformatik2010_Beitrag_Emotionserkennung_Christoph_Amma_et_al.pdf}, author={Amma, Christoph and Fischer, Andreas and Stein, Thorsten and Schwameder, Hermann and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2162.php} @inproceedings{schick2012vision, note={ICMI'14}, year={2012}, title={Vision-Based Handwriting Recognition for Unrestricted Text Input in Mid-Air}, booktitle={14th ACM International Conference on Multimodal Interaction}, author={Schick, Alexander and Morlock, Daniel and Amma, Christoph and Schultz, Tanja and Stiefelhagen, Rainer} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2128.php} @inproceedings{j2012initial, title={Initial Experiments with Tamil LVCSR}, year={2012}, note={IALP}, booktitle={The International Conference on Asian Language Processing, Hanoi, Vietnam}, author={J, Melvin Jose and Vu, Ngoc Thang and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2125.php} @inproceedings{povey2012generating, note={ICASSP}, title={Generating Exact Lattices in the WFST Framework}, year={2012}, booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/povey_lattice.pdf}, author={Povey, Daniel and Hannemann, Mirko and Boulianne, Gilles and Burget, Lukas and Ghoshal, Arnab and Janda, Milos and Karafiat, Martin and Kombrink, Stefan and Motlicek, Petr and Qian, Yanmin and Riedhammer, Korbinian and Vesely, Karel and Vu, Ngoc Thang} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2107.php} @inproceedings{weiner2012integration, title={Integration Of Language Identification Into A Recognition System For Spoken Conversations Containing Code-Switches}, year={2012}, note={SLTU'12}, booktitle={The third International Workshop on Spoken Languages Technologies for Under-resourced Languages}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/weiner_vu_sltu2012.pdf}, author={Weiner, Jochen and Vu, Ngoc Thang and Telaar, Dominic and Metze, Florian and Schultz, Tanja and Lyu, Dau-Cheng and Li, Eng-Siong Chng and Haizhou}, abstract={This paper describes the integration of language identification (LID) into a multilingual automatic speech recognition (ASR) system for spoken conversations containing code-switches between Mandarin and English. We apply a multistream approach to combine at frame level the acoustic model score and the language information, where the latter is provided by an LID component. Furthermore, we advance this multistream approach by a new method called “Language Lookahead”, in which the language information of subsequent frames is used to improve accuracy. Both methods are evaluated using a set of controlled LID results with varying frame accuracies. Our results show that both approaches improve the ASR performance by at least 4% relative if the LID achieves a minimum frame accuracy of 85%.}, } @inproceedings{amma2015advancing, author = {Amma, Christoph and Krings, Thomas and B\"{o}er, Jonas and Schultz, Tanja}, title = {Advancing Muscle-Computer Interfaces with High-Density Electromyography}, booktitle = {Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems}, series = {CHI '15}, year = {2015}, isbn = {978-1-4503-3145-6}, location = {Seoul, Republic of Korea}, pages = {929--938}, numpages = {10}, url = {http://doi.acm.org/10.1145/2702123.2702501}, doi = {10.1145/2702123.2702501}, acmid = {2702501}, publisher = {ACM}, address = {New York, NY, USA}, } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2108.php} @inproceedings{schlippe2012hausa, title={Hausa Large Vocabulary Continuous Speech Recognition}, year={2012}, note={SLTU'12}, booktitle={The third International Workshop on Spoken Languages Technologies for Under-resourced Languages, Cape Town, South Africa}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SLTU2012-Schlippe_Hausa.pdf}, author={Schlippe, Tim and Djomgang, Edy Guevara Komgang and Vu, Ngoc Thang and Schultz, Sebastian Ochs and Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2105.php} @inproceedings{vu2012multilingual, title={Multilingual Bottleneck Features and Its Application for Under-resourced Languages}, year={2012}, note={SLTU'12}, booktitle={The third International Workshop on Spoken Languages Technologies for Under-resourced Languages, Cape Town, South Africa}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/vu_sltu2012.pdf}, author={Vu, Ngoc Thang and Schultz, Florian Metze and Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2094.php} @inproceedings{vu2012initialization, note={Interspeech 2012}, year={2012}, title={Initialization Schemes for Multilayer Perceptron Training and Their Impact on ASR Performance using Multilingual Data}, booktitle={13th Annual Conference of the International Speech Communication Association, Portland, Oregon}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/vu_mlp_interspeech2012.pdf}, author={Vu, Ngoc Thang and Breiter, Wojtek and Metze, Florian and Schultz, and Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2079.php} @inproceedings{putze2010utterance, year={2010}, title={Utterance Selection for Speech Acts in a Cognitive Tourguide Scenario}, note={Interspeech 2010}, booktitle={11th Annual Conference of the International Speech Communication Association, Makuhari, Japan}, author={Putze, Felix and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2074.php} @inproceedings{janke2010impact, year={2010}, title={Impact of Lack of Acoustic Feedback in EMG-based Silent Speech Recognition}, note={Interspeech 2010}, booktitle={11th Annual Conference of the International Speech Communication Association, Makuhari, Japan}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/JankeWandSchultz_IS10.pdf}, abstract={This paper presents our recent advances in speech recognition based on surface electromyography (EMG). This technology allows for Silent Speech Interfaces since EMG captures the electrical potentials of the human articulatory muscles rather than the acoustic speech signal. Our earlier experiments have shown that the EMG signal is greatly impacted by the mode of speaking. In this study we extend this line of research by comparing EMG signals from audible, whispered, and silent speaking mode. We distinguish between phonetic features like consonants and vowels and show that the lack of acoustic feedback in silent speech implies an increased focus on somatosensoric feedback, which is visible in the EMG signal. Based on this analysis we develop a spectral mapping method to compensate for these differences. Finally, we apply the spectral mapping to the front-end of our speech recognition system and show that recognition rates on silent speech improve by up to 11.59% relative.}, keywords={EMG, EMG-based speech recognition, Silent Speech Interfaces, somatosensoric feedback}, author={Janke, Matthias and Wand, Michael and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2060.php} @inproceedings{ year={2012}, isbn={978-3-642-34480-0}, booktitle={Neural Information Processing}, volume={7664}, series={Lecture Notes in Computer Science}, editor={Huang, Tingwen and Zeng, Zhigang and Li, Chuandong and Leung, ChiSing}, doi={10.1007/978-3-642-34481-7_51}, title={Cross-Subject Classification of Speaking Modes Using fNIRS}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/HerffSchultz_ICONIP2012.pdf}, publisher={Springer Berlin Heidelberg}, keywords={fNIRS; BCI; speech imagery; cross-subject; session-transfer}, author={Herff, Christian and Heger, Dominic and Putze, Felix and Guan, Cuntai and Schultz, Tanja}, pages={417-424}, language={English} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2037.php} @inproceedings{schlippe2012automatic, title={Automatic Error Recovery for Pronunciation Dictionaries}, year={2012}, note={Interspeech 2012}, booktitle={13th Annual Conference of the International Speech Communication Association, Portland, Oregon}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Interspeech2012-Schlippe_DictFilter.pdf}, author={Schlippe, Tim and Ochs, Sebastian and Vu, Ngoc Thang and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2035.php} @inproceedings{schlippe2012grapheme, year={2012}, title={Grapheme-to-Phoneme Model Generation for Indo-European Languages}, note={ICASSP 2012}, booktitle={37th International Conference on Acoustics, Speech, and Signal Processing, Kyoto, Japan}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ICASSP2012-Schlippe_G2PModelGenerationIndoEuropean.pdf}, author={Schlippe, Tim and Ochs, Sebastian and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2034.php} @inproceedings{vu2012a, title={A First Speech Recognition System For Mandarin-English Code-Switch Conversational Speech}, year={2012}, note={ICASSP 2012}, booktitle={37th International Conference on Acoustics, Speech, and Signal Processing, Kyoto, Japan}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ICASSP2012-Vu_CodeSwitch.pdf}, author={Vu, Ngoc Thang and Lyu, Dau-Cheng and Weiner, Jochen and Telaar, Dominic and Schlippe, Tim and Blaicher, Fabian and Chng, Eng-Siong and Schultz, Tanja and Li, Haizhou}, abstract={This paper presents first steps toward a large vocabulary continuous speech recognition system (LVCSR) for conversational Mandarin-English code-switching (CS) speech. We applied state-of-the-art techniques such as speaker adaptive and discriminative training to build the first baseline system on the SEAME corpus [1] (South East Asia Mandarin-English). For acoustic modeling, we applied different phone merging approaches based on the International Phonetic Alphabet (IPA) and Bhattacharyya distance in combination with discriminative training to improve accuracy. On language model level, we investigated statistical machine translation (SMT) - based text generation approaches for building code-switching language models. Furthermore, we integrated the provided information from a language identification system (LID) into the decoding process by using a multi-stream approach. Our best 2-pass system achieves a Mixed Error Rate (MER) of 36.6% on the SEAME development set.}, } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2033.php} @inproceedings{lamel2011speech, title={Speech Recognition for Machine Translation in Quaero}, year={2011}, note={IWSLT 2011}, booktitle={The International Workshop on Spoken Language Translation, San Francisco, USA}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/IWSLT2011-Schlippe_SpeechRecognitionQuaero.pdf}, author={Lamel, Lori and Courcinous, Sandrine and Despres, Julien and Gauvain, Jean-Luc and Josse, Yvan and Kilgour, Kevin and Kraft, Florian and Bac, Le Viet and Ney, Hermann and Nußbaum-Thom, Markus and Oparin, Ilya and Schlippe, Tim and Schlüter, Ralf and Schultz, Tanja and Silva, Thiago Fraga Da and Stüker, Sebastian and Sundermeyer, Martin and Vieru, Bianca and Vu, Ngoc Thang and Waibel, Alexander and Woehrling, Cécile} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2032.php} @inproceedings{schlippe2010text, title={Text Normalization based on Statistical Machine Translation and Internet User Support}, year={2010}, note={Interspeech 2010}, booktitle={11th Annual Conference of the International Speech Communication Association, Makuhari, Japan}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Interspeech2010-Schlippe_SMTNormalization.pdf}, author={Schlippe, Tim and Zhu, Chenfei and Gebhardt, Jan and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2011.php} @INPROCEEDINGS{6346279, author={Herff, C. and Putze, F. and Heger, D. and Cuntai Guan and Schultz, T.}, booktitle={Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE}, title={Speaking mode recognition from functional Near Infrared Spectroscopy}, year={2012}, pages={1715-1718}, abstract={Speech is our most natural form of communication and even though functional Near Infrared Spectroscopy (fNIRS) is an increasingly popular modality for Brain Computer Interfaces (BCIs), there are, to the best of our knowledge, no previous studies on speech related tasks in fNIRS-based BCI. We conducted experiments on 5 subjects producing audible, silently uttered and imagined speech or do not produce any speech. For each of these speaking modes, we recorded fNIRS signals from the subjects performing these tasks and distinguish segments containing speech from those not containing speech, solely based on the fNIRS signals. Accuracies between 69% and 88% were achieved using support vector machines and a Mutual Information based Best Individual Feature approach. We are also able to discriminate the three speaking modes with 61% classification accuracy. We thereby demonstrate that speech is a very promising paradigm for fNIRS based BCI, as classification accuracies compare very favorably to those achieved in motor imagery BCIs with fNIRS.}, keywords={brain-computer interfaces;infrared spectra;speech recognition;support vector machines;audible speech;best individual feature approach;brain computer interface;functional near infrared spectroscopy;imagined speech;mutual information;silently uttered speech;speaking mode recognition;support vector machine;Accuracy;Brain;Feature extraction;Hemodynamics;Mutual information;Spectroscopy;Speech;Adult;Corpus Callosum;Electrodes;Hemodynamics;Humans;Male;Motor Cortex;Spectroscopy, Near-Infrared;Speech}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/HerffSchultzEMBC_2012.pdf}, doi={10.1109/EMBC.2012.6346279}, ISSN={1557-170X}, month={Aug},} @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_2009.php} @inproceedings{heger2012filling, note={EMBC'12}, title={Filling a Glass of Water: Continuously Decoding the Speed of 3D Hand Movements from EEG Signals}, year={2012}, booktitle={International Conference of the IEEE Engineering in Medicine and Biology Society, San Diego, USA}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/embc2012_fillingAGlass.pdf}, author={Heger, Dominic and Jäkel, Rainer and Putze, Felix and Lösch, Martin and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1960.php} @inproceedings{wand2012decision, year={2012}, title={Decision-tree based Analysis of Speaking Mode Discrepancies in EMG-based Speech Recognition}, note={BIOSIGNALS 2012}, booktitle={International Conference on Bio-inspired Systems and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/WandJankeSchultz_BS2012_DecisionTreeAnalysis.pdf}, abstract={This study is concerned with the impact of speaking mode variabilities on speech recognition by surface electromyography (EMG). In EMG-based speech recognition, we capture the electric potentials of the human articulatory muscles by surface electrodes, so that the resulting signal can be used for speech processing. This enables the user to communicate silently, without uttering any sound. Previous studies have shown that the processing of silent speech creates a new challenge, namely that EMG signals of audible and silent speech are quite distinct. In this study we consider EMG signals of three speaking modes: audibly spoken speech, whispered speech, and silently mouthed speech. We present an approach to quantify the differences between these speaking modes by means of phonetic decision trees and show that this measure correlates highly with differences in the performance of a recognizer on the different speaking modes. We furthermore reinvestigate the spectral mapping algorithm, which reduces the discrepancy between different speaking modes, and give an evaluation of its effectiveness.}, author={Wand, Michael and Janke, Matthias and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1965.php} @inproceedings{johner2012inferring, title={Inferring Prosody from Facial Cues for EMG-based Synthesis of Silent Speech}, year={2012}, booktitle={4th International Conference on Applied Human Factors and Ergonomics}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/johner_christian_ahfe_paper.pdf}, abstract={In this paper we introduce a system which is able to detect prosodic elements in a spoken utterance based on signals from the facial muscles. The proposed system can augment our surface electromyography (EMG) based Silent Speech Interface in order to make synthesized speech more natural. Having shown in (Nakamura, Janke, Wand, & Schultz, 2011) that it is possible to produce understandable synthesized speech from EMG signals, our current interest is to improve the quality and expressivity of the synthesis. We show that a standard phonetically balanced German speech corpus with only a few additional utterances is sufficient to train a system that can discriminate yes/no questions from normal speech and also distinguish between normal and emphasized words in an utterance. For the detection of prosodic information in facial muscle movement we extend our EMG based speech synthesis system with two additional EMG channels, recording the movements of the facial muscles musculus corrugator and musculus frontalis. Our classification method uses a frame-based SVM classification, followed by a majority vote to classify a whole word. Our system achieves F-scores of up to 0.68 for the recognition of emphasized words and 1.0 for the classification between questions and normal utterances although the results show large variations depending on the feature combination used for training.}, keywords={EMG, synthesis, prosody, speech recognition}, author={Johner, Christian and Janke, Matthias and Wand, Michael and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1962.php} @inproceedings{janke2012further, year={2012}, title={Further Investigations on EMG-to-Speech Conversion}, note={ICASSP}, booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Janke_FurtherInvestigationsEMG2F0.pdf}, abstract={Our study deals with a Silent Speech Interface based onmapping surface electromyographic (EMG) signals to speech waveforms. Electromyographic signals recorded from the facial muscles capture the activity of the human articulatory apparatus and therefore allow to retrace speech, even when no audible signal is produced. The mapping of EMG signals to speech is done via a Gaussian mixture model (GMM)-based conversion technique. In this paper, we follow the lead of EMG-based speech-to-text systems and apply two major recent technological advances to our system, namely, we consider session- independent systems, which are robust against electrode repositioning, and we show that mapping the EMG signal to whispered speech creates a better speech signal than a mapping to normally spoken speech. We objectively evaluate the performance of our systems u sing a spectral distortion measure.}, keywords={Silent Speech, Electromyography,Speech Synthesis, Voice Conversion}, author={Janke, Matthias and Wand, Michael and Nakamura, Keigo and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1077.php} @inproceedings{amma2010airwriting, year={2010}, title={Airwriting Recognition using Wearable Motion Sensors}, booktitle={First Augmented Human International Conference}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/1405.php}, author={Amma, Christoph and Gehrig, Dirk and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1936.php} @inproceedings{kuehne2012on, note={VISAPP 2012}, year={2012}, title={On-line Action Recognition from sparse Feature Flow}, booktitle={International Conference on Computer Vision Theory and Applications 2012}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/paper_visapp2012.pdf}, author={Kuehne, Hildegard and Gehrig, Dirk and Schultz, Tanja and Stiefelhagen, Rainer} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1914.php} @inproceedings{amma2012airwriting, title={Airwriting: Hands-free Mobile Text Input by Spotting and Continuous Recognition of 3d-Space Handwriting with Inertial Sensors}, year={2012}, note={ISWC '12}, booktitle={16th International Symposium on Wearable Computers}, author={Amma, Christoph and Georgi, Marcus and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1911.php} @inproceedings{amma2012airwriting, note={IUI '12}, year={2012}, title={Airwriting: demonstrating mobile text input by 3D-space handwriting}, booktitle={International Conference on Intelligent User Interfaces}, author={Amma, Christoph and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1059.php} @inproceedings{nakamura2011estimation, year={2011}, title={Estimation of Fundamental Frequency from Surface Electromyographic Data}, booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/NakamuraSchultz_ICASSP2011.pdf}, abstract={In this paper, we present our recent studies of $F_0$ estimation from the surface electromyographic (EMG) data using a Gaussian mixture model (GMM)-based voice conversion (VC) technique, referred to as EMG-to-$F_0$. In our approach, a support vector machine recognizes individual frames as unvoiced and voiced (U/V), and voiced $F_0$ contours are discriminated by the trained GMM based on the manner of minimum mean-square error. EMG-to-$F_0$ is experimentally evaluated using three data sets of different speakers. Each data set includes almost 500 utterances. Objective experiments demonstrate that we achieve a correlation coefficient of up to 0.49 between estimated and target $F_0$ contours with more than 84% U/V decision accuracy, although the results have large variations.}, keywords={Electromyography, Voice conversion, Fundamental frequency, Feature estimation}, author={Nakamura, Keigo and Janke, Matthias and Wand, Michael and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1054.php} @inproceedings{nallasamy2011analysis, title={Analysis of Dialectal Influence in Pan-Arabic ASR}, year={2011}, note={Interspeech 2011}, booktitle={12th Annual Conference of the International Speech Communication Association}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/NallasamySchultz_Interspeech2011.pdf}, author={Nallasamy, Udhay and Garbus, Michael and Metze, Florian and Jin, Qin and Schaaf, Thomas and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1053.php} @inproceedings{hsiao2011generalized, year={2011}, title={Generalized Baum-Welch Algorithm and Its Implication to a New Extended Baum-Welch Algorithm}, note={Interspeech 2011}, booktitle={12th Annual Conference of the International Speech Communication Association}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/HsiaoSchultz_Interspeech2011.pdf}, author={Hsiao, Roger and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1055.php} @inproceedings{yang2011investigation, title={Investigation of Cross-show Speaker Diarization}, year={2011}, note={Interspeech 2011}, booktitle={12th Annual Conference of the International Speech Communication Association}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/YangJinSchultz_Interspeech2011.pdf}, author={Yang, Qian and Jin, Qin and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1052.php} @inproceedings{vu2011rapid, year={2011}, title={Rapid building of an ASR system for Under-Resourced Languages based on Multilingual Unsupervised Training}, note={Interspeech 2011}, booktitle={12th Annual Conference of the International Speech Communication Association}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/VuKrausSchultz_Interspeech2011.pdf}, author={Vu, Ngoc Thang and Kraus, Franziska and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1056.php} @inproceedings{janke2011investigations, title={Investigations on Speaking Mode Discrepancies in EMG-based Speech Recognition}, year={2011}, note={Interspeech 2011}, booktitle={12th Annual Conference of the International Speech Communication Association}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/WandJankeSchultz_Interspeech2011.pdf}, abstract={In this paper we present our recent study on the impact of speaking mode variabilities on speech recognition by surface electromyography (EMG). Surface electromyography captures the electric potentials of the human articulatory muscles, which enables a user to communicate naturally without making any audible sound. Our previous experiments have shown that the EMG signal varies greatly between different speaking modes, like audibly uttered speech and silently articulated speech. In this study we extend our previous research and quantify the impact of different speaking modes by investigating the amount of mode-specific leaves in phonetic decision trees. We show that this measure correlates highly with discrepancies in the spectral energy of the EMG signal, as well as with differences in the performance of a recognizer on different speaking modes. We furthermore present how EMG signal adaptation by spectral mapping decreases the effect of the speaking mode.}, keywords={EMG, EMG-based speech recognition, Silent Speech Interfaces, phonetic decision tree}, author={Janke, Matthias and Wand, Michael and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1051.php} @inproceedings{herff2011impact, year={2011}, title={Impact of Different Feedback Mechanisms in EMG-based Speech Recognition}, note={Interspeech 2011}, booktitle={12th Annual Conference of the International Speech Communication Association}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/HerffSchultz_Interspeech2011.pdf}, abstract={This paper reports on our recent research in the feedback effects of Silent Speech. Our technology is based on surface electromyography (EMG) which captures the electrical potentials of the human articulatory muscles rather than the acoustic speech signal. While recognition results are good for loudly articulated speech and when experienced users speak silently, novice users usually achieve far worse results when speaking silently. Since there is no acoustic feedback when speaking silently, we investigate different kinds of feedback modes: no additional feedback except the natural somatosensory feedback (like the touching of the lips), visual feedback using a mirror and indirect acoustic feedback by speaking simultaneously to a previously recorded audio signal. In addition we examine recorded EMG data when the subject speaks audibly and silently in a loud environment to see if the Lombard effect can be observed in Silent Speech, too.}, keywords={Silent speech, Elecromyography, Lack of acoustic feedback, EMG-based speech recognition, Lombard effect}, author={Herff, Christian and Janke, Matthias and Wand, Michael and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1047.php} @inproceedings{jarvis2011multimodal, year={2011}, title={Multimodal Person Independent Recognition of Workload Related Biosignal Patterns}, booktitle={International Conference on Multimodal Interaction, ICMI 2011}, author={Jarvis, Jan-Philip and Putze, Felix and Heger, Dominic and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1061.php} @inproceedings{wand2011session, title={Session-Independent EMG-based Speech Recognition}, year={2011}, booktitle={International Conference on Bio-inspired Systems and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/WandSchultz_Biosignals2011.pdf}, author={Wand, Michael and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1049.php} @inproceedings{gehrig2011combined, year={2011}, title={Combined Intention, Activity, and Motion Recognition for a Humanoid Household Robot}, booktitle={IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2011}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Gehrig_IROS2011.pdf}, author={Gehrig, Dirk and Krauthausen, Peter and Rybok, Lukas and Kuehne, Hildegard and Hanebeck, Uwe D. and Schultz, Tanja and Stiefelhagen, Rainer} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1058.php} @inproceedings{vu2011cross, title={Cross-language bootstrapping based on completely unsupervised training using multilingual A-stabil}, year={2011}, booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/VuKrausSchultz_ICASSP2011.pdf}, author={Vu, Ngoc Thang and Kraus, Franziska and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1060.php} @inproceedings{wand2011analysis, title={Analysis of Phone Confusion in EMG-based Speech Recognition}, year={2011}, booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/WandSchultz_ICASSP2011.pdf}, author={Wand, Michael and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1048.php} @inproceedings{heger2011online, year={2011}, title={Online Recognition of Facial Actions for natural EEG-based BCI Applications}, booktitle={Affective Computing and Intelligent Interaction 2011, ACII 2011}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/acii11_facialActions.pdf}, author={Heger, Dominic and Putze, Felix and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1075.php} @inproceedings{vu2010optimization, year={2010}, title={Optimization On Vietnamese Large Vocabulary Speech Recognition}, booktitle={2nd Workshop on Spoken Languages Technologies for Under-resourced Languages}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/vu_SLTU2010_VNASR2.pdf}, author={Vu, Ngoc Thang and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1064.php} @inproceedings{metze2010the, year={2010}, title={The 2010 CMU GALE Speech-to-Text System}, booktitle={Interspeech 2010}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/MetzeSchultz_IS10.pdf}, author={Metze, Florian and Hsiao, Roger and Jin, Qin and Nallasamy, Udhay and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1074.php} @inproceedings{gehrig2010erkennung, title={Erkennung von menschlichen Bewegungen mit Hidden Markov Modellen}, year={2010}, booktitle={Sportinformatik trifft Sporttechnologie, Tagung der dvs-Sektion Sportinformatik in Kooperation mit der deutschen interdisziplin}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Gehrig_DVS10_Bewegungserkennung_mit_HMMs.pdf}, author={Gehrig, Dirk and Kühne, Hildegard and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1063.php} @inproceedings{heger2010an, title={An Adaptive Information System for an Empathic Robot using EEG Data}, year={2010}, booktitle={International Conference on Social Robotics}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/HegerPutzeSchultz_ICSR10.pdf}, author={Heger, Dominic and Putze, Felix and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1062.php} @inproceedings{vu2010multilingual, year={2010}, title={Multilingual A-stabil: A new confidence score for multilingual unsupervised training}, booktitle={IEEE Workshop on Spoken Language Technology}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/vu_mut_slt2010.pdf}, author={Vu, Ngoc Thang and Kraus, Franziska and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1078.php} @inproceedings{janke2010spectral, note={Side event of Biosignals 2010 conference}, year={2010}, title={Spectral Energy Mapping for EMG-based Recognition of Silent Speech}, booktitle={First International Workshop on Bio-inspired Human-Machine Interfaces and Healthcare Applications}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/WandSchultz_BInterface2010.pdf}, abstract={This paper reports on our latest study on speech recognition based on surface electromyography (EMG). This technology allows for Silent Speech Interfaces since EMG captures the electrical potentials of the human articulatory muscles rather than the acoustic speech signal. Therefore, our technology enables speech recognition to be applied to silently mouthed speech. Earlier experiments indicate that the EMG signal is greatly impacted by the mode of speaking. In this study we analyze and compare EMG signals from audible, whispered, and silent speech. We quantify the differences and develop a spectral mapping method to compensate for these differences. Finally, we apply the spectral mapping to the front-end of our speech recognition system and show that recognition rates on silent speech improve by up to 12.3% relative.}, author={Janke, Matthias and Wand, Michael and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1076.php} @inproceedings{putze2010multimodal, title={Multimodal Recognition of Cognitive Workload for Multitasking in the Car}, year={2010}, booktitle={20th International Conference on Pattern Recognition}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/PutzeJarvisSchultz_ICPR10.pdf}, author={Putze, Felix and Jarvis, Jan-Philip and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1071.php} @inproceedings{heger2010online, title={Online Workload Recognition from EEG data during Cognitive Tests and Human-Computer Interaction}, year={2010}, booktitle={33rd Annual German Conference on Artificial Intelligence 2010}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/HegerPutzeSchultz_KI10.pdf}, author={Heger, Dominic and Putze, Felix and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1073.php} @inproceedings{gehrig2010towards, title={Towards Semantic Segmentation of Human Motion Sequences}, year={2010}, booktitle={33rd Annual German Conference on Artificial Intelligence 2010}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/gehrig_ki2010.pdf}, author={Gehrig, Dirk and Stein, Thorsten and Fischer, Andreas and Schwameder, Hermann and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1072.php} @inproceedings{heger2010biosignalsstudio, year={2010}, title={BiosignalsStudio: A flexible Framework for Biosignal Capturing and Processing}, booktitle={33rd Annual German Conference on Artificial Intelligence 2010}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/HegerPutzeAmmaSchultz_KI10.pdf}, author={Heger, Dominic and Putze, Felix and Amma, Christoph and Wielatt, Thomas and Plotkin, Igor and Wand, Michael and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1068.php} @inproceedings{schlippe2010wiktionary, note={Interspeech 2010}, title={Wiktionary as a Source for Automatic Pronunciation Extraction}, year={2010}, booktitle={11th Annual Conference of the International Speech Communication Association, Makuhari, Japan}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SchlippeOchsSchultz_IS10.pdf}, author={Schlippe, Tim and Ochs, Sebastian and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1065.php} @inproceedings{hsiao2010improvements, year={2010}, title={Improvements to Generalized Discriminative Feature Transformation for Speech Recognition}, booktitle={11th Annual Conference of the International Speech Communication Association}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/MetzeSchultz_IS10.pdf}, author={Hsiao, Roger and Metze, Florian and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1066.php} @inproceedings{vu2010rapid, title={Rapid Bootstrapping of five Eastern European Languages using the Rapid Language Adaptation Toolkit}, year={2010}, note={Interspeech 2010}, booktitle={11th Annual Conference of the International Speech Communication Association, Makuhari, Japan}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/VuSchultz_IS10.pdf}, author={Vu, Ngoc Thang and Schlippe, Tim and Kraus, Franziska and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1103.php} @inproceedings{wand2009towards, note={Biosignals 2009}, year={2009}, title={Towards Speaker-Adaptive Speech Recognition based on Surface Electromyography}, booktitle={2nd International Conference on Bio-inspired Systems and Signal Processing, Porto, Portugal}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/WandSchultz_Biosignals2009.pdf}, author={Wand, Michael and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1104.php} @inproceedings{porbadnigk2009eeg, title={EEG-based Speech Recognition - Impact of Temporal Effects}, year={2009}, note={Biosignals 2009}, booktitle={2nd International Conference on Bio-inspired Systems and Signal Processing, Porto, Portugal}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Biosignals_paper114.pdf}, author={Porbadnigk, Anne and Wester, Marek and Callies, Jan Peter and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1096.php} @inproceedings{tam2009incorporating, title={Incorporating Monolingual Corpora into Bilingual Latent Semantic Analysis for Crosslingual LM Adaptation}, year={2009}, booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/TamSchultz-ICASSP2009.pdf}, author={Tam, Yik-Cheung and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1094.php} @inproceedings{jin2009voice, title={Voice Convergin: Speaker De-Identification by Voice Transformation}, year={2009}, booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/JinSchultz-ICASSP2009.pdf}, author={Jin, Qin and Toth, Arthur and Schultz, Tanja and Black, Alan W} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1097.php} @inproceedings{fuhs2009detecting, year={2009}, title={Detecting Bandlimited Audio in Broadcast Television Shows}, booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/FuhsSchultz-ICASSP2009.pdf}, author={Fuhs, Mark and Jin, Qin and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1098.php} @inproceedings{hsiao2009generalized, title={Generalized Baum-Welch Algorithm for Discriminative Training on Large Vocabulary}, year={2009}, booktitle={Continuous Speech Recognition Systems}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/HsiaoSchultz-ICASSP2009.pdf}, author={Hsiao, Roger and Tam, Yik-Cheung and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1079.php} @inproceedings{stoimenov2009a, year={2009}, title={A Multiplatform Speech Recognition Decoder Based on Weighted Finite-State Transducers}, booktitle={Automatic Speech Recognition and Understanding}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/StoimenovSchultz_ASRU2009.pdf}, author={Stoimenov, Emilian and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1080.php} @inproceedings{jin2009speaker, year={2009}, title={Speaker De-Identification Via Voice Transformation}, booktitle={Automatic Speech Recognition and Understanding}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/JinTothSchultzBlack-ASRU2009.pdf}, author={Jin, Qin and Toth, Arthur and Black, Alan W and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1081.php} @inproceedings{vu2009vietnamese, title={Vietnamese Large Vocabulary Continuous Speech Recognition}, year={2009}, booktitle={Automatic Speech Recognition and Understanding}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/VuSchultz_ASRU2009.pdf}, author={Vu, Ngoc Thang and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1133.php} @inproceedings{fischer2008bewegungserkennung, year={2008}, title={Bewegungserkennung mit Hidden Markov Modellen}, booktitle={Landessymposium}, author={Fischer, Andreas and Stein, Thorsten and Gehrig, Dirk and Schultz, Tanja and Schwameder, Hermann} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1083.php} @inproceedings{gehrig2009hmm, title={HMM-based Human Motion Recognition with Optical Flow Data}, year={2009}, booktitle={9th IEEE-RAS International Conference on Humanoid Robots, Workshop Imitation and Coaching in Humanoid Robots}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Humanoids2009_final.pdf}, author={Gehrig, Dirk and Kühne, Hildegard and Wörner, Annika and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1101.php} @inproceedings{fischer2009training, title={Training und Erkennung mit Hidden Markov Modellen bei unterschiedlichen Geh-/Laufgeschwindigkeiten}, year={2009}, booktitle={Biomechanik - Grundlagenforschung und Anwendung, Tagung der dvs-Sektion Biomechanik}, author={Fischer, Andreas and Stein, Thorsten and Gehrig, Dirk and Schultz, Tanja and Schwameder, Hermann} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1091.php} @inproceedings{putze2009cognitive, year={2009}, title={Cognitive Dialog Systems for Dynamic Environments: Progress and Challenges}, booktitle={4th Biennial Workshop on DSP for In-Vehicle Systems and Safety}, author={Putze, Felix and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1090.php} @inproceedings{schultz2009towards, title={Towards Emotion Recognition from Electroencephalographic Signals}, year={2009}, booktitle={2009 International Conference on Affective Computing & Intelligent Interaction}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ACII09_Schaaff.pdf}, author={Schultz, Tanja and Schaaff, Kristina} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1082.php} @inproceedings{putze2009cognitive, year={2009}, title={Cognitive Memory Modeling for Interactive Systems in Dynamic Environments}, booktitle={1st International Workshop on Spoken Dialog Systems}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/PutzeSchultz_IWSDS09.pdf}, author={Putze, Felix and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1084.php} @inproceedings{schaaff2009towards, title={Towards an EEG-based Emotion Recognizer for Humanoid Robots}, year={2009}, booktitle={18th IEEE International Symposium on Robot and Human Interactive Communication}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ROMAN09-Schaaff.pdf}, author={Schaaff, Kristina and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1087.php} @inproceedings{li2009improving, title={Improving Speaker Segmentation via Speaker Identification and Text Segmentation}, year={2009}, booktitle={10th Annual Conference of the International Speech Communication Association}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Interspeech09_Li.pdf}, author={Li, Runxin and Jin, Qin and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1089.php} @inproceedings{hsiao2009generalized, year={2009}, title={Generalized Discriminative Feature Transformation for Speech Recognition}, booktitle={10th Annual Conference of the International Speech Communication Association}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Interspeech09_Hsiao.pdf}, author={Hsiao, Roger and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1086.php} @inproceedings{wand2009impact, title={Impact of Different Speaking Modes on EMG-based Speech Recognition}, year={2009}, booktitle={10th Annual Conference of the International Speech Communication Association}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Interspeech09_Wand_01.pdf}, author={Wand, Michael and Toth, Arthur and Jou, Szu-Chen (Stan) and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1088.php} @inproceedings{wölfel2009speaker, title={Speaker Identification using Warped MVDR Cepstral Features}, year={2009}, booktitle={10th Annual Conference of the International Speech Communication Association}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Interspeech09_Woelfel.pdf}, author={Wölfel, Matthias and Yang, Qian and Jin, Qin and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1085.php} @inproceedings{toth2009synthesizing, year={2009}, title={Synthesizing Speech from Electromyography using Voice Transformation Techniques}, booktitle={10th Annual Conference of the International Speech Communication Association}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Interspeech09_Toth.pdf}, author={Toth, Arthur and Wand, Michael and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1093.php} @inproceedings{schaaff2009eeg, year={2009}, title={EEG-based Emotion Recognition Using Support Vector Machines}, booktitle={1. Fachtagung Biophysiologische Interfaces}, author={Schaaff, Kristina and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1092.php} @inproceedings{putze2009towards, title={Towards Cognitive Dialog Systems}, year={2009}, booktitle={1. Fachtagung Biophysiologische Interfaces}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/cognitive_dialog_systems_01.pdf}, author={Putze, Felix and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1412.php} @inproceedings{gibert2009enhancement, note={CHISIG}, title={Enhancement of human computer interaction with facial electromyographic sensors}, year={2009}, booktitle={23nd conference of the computer-human interaction special interest group of Australia on Computer-human interaction: design (OZCHI 2009), Melbourne, Australia}, author={Gibert, Guillaume and Pruzinec, Martin and Schultz, Tanja and Stevens, Catherine} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1102.php} @inproceedings{fischer2009bewegungserkennung, note={}, title={Bewegungserkennung mit Hidden Markov Modellen}, year={2009}, booktitle={Informations- und Kommunikationstechnologien in der Sportmotorik, 11. Tagung der dvs-Sektion Sportmotorik}, author={Fischer, Andreas and Stein, Thorsten and Gehrig, Dirk and Schultz, Tanja and Schwameder, Hermann} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1132.php} @inproceedings{jou2008ears, year={2008}, title={EARS: Electromyographical Automatic Recognition of Speech}, note={Biosignals 2008}, booktitle={1st International Conference on Bio-inspired Systems and Signal Processing, Madeira, Portugal}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/JouSchultz_Biosignals2008.pdf}, author={Jou, Szu-Chen (Stan) and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1106.php} @inproceedings{charoenpornsawat2008improving, title={Improving Word Segmentation for Thai Speech Translation}, year={2008}, booktitle={IEEE Workshop on Spoken Language Technology}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SLT2008-CharoenpornsawatSchultz.pdf}, author={Charoenpornsawat, Paisarn and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1127.php} @inproceedings{schultz2008rapid, title={Rapid Language Adaptation Tools and Technologies for Multilingual Speech Processing}, year={2008}, booktitle={ICASSP}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/laskowskiICASSP2008_published.pdf}, author={Schultz, Tanja and Black, Alan W} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1105.php} @inproceedings{fung)2008rapid, year={2008}, title={Rapid Language Adaptation Tools & Technologies for Multilingual Speech Processing Systems}, booktitle={IEEE Workshop on Spoken Language Technology}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SLT2008-CharoenpornsawatSchultz.pdf}, author={Fung), (Presented by Pascale and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1131.php} @inproceedings{honal2008determine, year={2008}, title={Determine Task Demand from Brain Activity}, note={Biosignals 2008}, booktitle={1st International Conference on Bio-inspired Systems and Signal Processing, Madeira, Portugal}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/HonalSchultz_Biosignals2008.pdf}, author={Honal, Matthias and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1124.php} @inproceedings{schultz2008multilingual, year={2008}, title={Multilingual Speech Processing in the context of Under-resourced Languages}, booktitle={SLTU: Workshop on Spoken Language Technologies for Under-Resourced Languages}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SLTU2008-TSchultz.pdf}, author={Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1125.php} @inproceedings{kominek2008synthesizer, title={Synthesizer Voice Quality of New Languages Calibrated with Mean Mel Cepstral Distortion}, year={2008}, booktitle={SLTU: Workshop on Spoken Language Technologies for Under-Resourced Languages}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/kominek_black.sltu_2008.pdf}, author={Kominek, John and Schultz, Tanja and Black, Alan W} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1118.php} @inproceedings{heldner2008prosodic, title={Prosodic Features in the Vicinity of Silences and Overlaps}, year={2008}, booktitle={Nordic Prosody X}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/HeldnerEdlundLaskowskiPelce_NP08_ProsodicFeatures.pdf}, author={Heldner, Mattias and Edlund, Jens and Laskowski, Kornel and Pelcé, Antoine} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1108.php} @inproceedings{tam2008correlated, year={2008}, title={Correlated Bigram LSA for Unsupervised LM adaptation}, booktitle={Neural Information Processing Systems}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/TamSchultz_NIPS08_CorrelatedBigramLSA.pdf}, author={Tam, Yik-Cheung and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1121.php} @inproceedings{jin2008compensation, title={Compensation Approaches for Far-field Speaker Identification}, year={2008}, booktitle={NIST SRE Workshop 2008}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/NIST-SRE-2008.pdf}, author={Jin, Qin and Kumar, Kshitiz and Schultz, Tanja and Stern, Richard M} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1112.php} @inproceedings{schlippe2008diacritization, title={Diacritization as a Translation Problem and as a Sequence Labeling Problem}, year={2008}, note={AMTA 2008}, booktitle={Eighth Conference of the Association for Machine Translation in the Americas, Waikiki, Hawai'i}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/AMTA-2008-Schlippe.pdf}, author={Schlippe, Tim and Nguyen, ThuyLinh and Vogel, Stephan} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1123.php} @inproceedings{burger2008a, title={A Comparative Cross-Domain Study of the Occurrence of Laughter in Meeting and Seminar Corpora}, year={2008}, booktitle={6th International Conference on Language Resources and Evaluation}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/815_paper.pdf}, author={Burger, Susanne and Laskowski, Kornel and Wölfel, Matthias} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1117.php} @inproceedings{laskowski2008detection, title={Detection of Laughter-in-Interaction in Multichannel Close-Talk Microphone Recordings of Meetings}, year={2008}, booktitle={5th Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/laskowskiMLMI2008.pdf}, author={Laskowski, Kornel and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1126.php} @inproceedings{laskowski2008learning, year={2008}, title={Learning Prosodic Sequences Using the Fundamental Frequency Variation Spectrum}, booktitle={4th International Conference on Speech Prosody}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/laskowskiPROSODY2008_A.pdf}, author={Laskowski, Kornel and Edlund, Jens and Heldner, Mattias} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1122.php} @inproceedings{laskowski2008the, title={The Fundamental Frequency Variation Spectrum}, year={2008}, booktitle={21st Swedish Phonetics Conference}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/laskowski_heldner_edlund_newer.pdf}, author={Laskowski, Kornel and Heldner, Mattias and Edlund, Jens} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1107.php} @inproceedings{gehrig2008selecting, year={2008}, title={Selecting Relevant Features for Human Motion Recognition}, booktitle={19th International Conference on Pattern Recognition}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/icpr2008_final.pdf}, author={Gehrig, Dirk and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1119.php} @inproceedings{laskowski2008computing, year={2008}, title={Computing the Fundamental Frequency Variation Spectrum in Conversational Spoken Dialogue Systems}, booktitle={155th Meeting of the Acoustical Society of America}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/003228.pdf}, author={Laskowski, Kornel and Wölfel, Matthias and Heldner, Mattias and Edlund, Jens} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1113.php} @inproceedings{hsiao2008the, year={2008}, title={The CMU-InterACT 2008 Mandarin Transcription System}, booktitle={9th Annual Conference of the International Speech Communication Association}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/HsiaoSchultz-IS2008.pdf}, author={Hsiao, Roger and Fuhs, Mark and Tam, Wilson (Yik-Cheung) and Jin, Qin and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1116.php} @inproceedings{jin2008robust, year={2008}, title={Robust Far-Field Speaker Recognition under Mismatched Conditions}, booktitle={9th Annual Conference of the International Speech Communication Association}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/JinSchultz-IS2008.pdf}, author={Jin, Qin and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1114.php} @inproceedings{laskowski2008recovering, year={2008}, title={Recovering Participant Identities in Meetings from a Probabilistic Description of Vocal Interaction}, booktitle={9th Annual Conference of the International Speech Communication Association}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/LaskowskiSchultz-IS2008.pdf}, author={Laskowski, Kornel and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1115.php} @inproceedings{kominek2008improving, title={Improving Speech Systems Built From Very Little Data}, year={2008}, booktitle={9th Annual Conference of the International Speech Communication Association}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/KominekSchultz-IS2008.pdf}, author={Kominek, John and Badaskar, Sameer and Black, Alan W and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1109.php} @inproceedings{gehrig2008online, title={Online Recognition of Daily-Life Movements}, year={2008}, booktitle={8th IEEE-RAS International Conference on Humanoid Robots, Workshop Imitation and Coaching in Humanoid Robots}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Humanoids2008a.pdf}, author={Gehrig, Dirk and Fischer, Andreas and Kühne, Hildegard and Stein, Thorsten and Wörner, Annika and Schwameder, Hermann and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1130.php} @inproceedings{jin2008is, title={Is Voice Transformation A Threat To Speaker Identification?}, year={2008}, booktitle={33rd IEEE International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/JinSchultz-ICASSP2008.pdf}, author={Jin, Qin and Toth, Arthur and Black, Alan W and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1120.php} @inproceedings{laskowski2008modeling, title={Modeling Vocal Interaction for Text-Independent Participant Characterization in Multi-Party Conversation}, year={2008}, booktitle={9th SIGdial Workshop on Discourse and Dialogue}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SIGDIAL24.pdf}, author={Laskowski, Kornel and Ostendorf, Mari and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1129.php} @inproceedings{paulik2008sentence, title={Sentence Segmentation and Punctuation Recovery For Spoken Language Translation}, year={2008}, booktitle={33rd IEEE International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/PaulikSchultz-ICASSP2008.pdf}, author={Paulik, Matthias and Rao, Sharath and Lane, Ian and Vogel, Stephan and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1128.php} @inproceedings{laskowski2008an, title={An Instantaneous Vector Representation of Delta Pitch for Speaker-Change Prediction in Conversational Dialogue Systems}, year={2008}, booktitle={33rd IEEE International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/laskowskiICASSP2008_published.pdf}, author={Laskowski, Kornel and Edlund, Jens and Heldner, Mattias} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1432.php} @inproceedings{do2008transfer, title={Transfer of Human Movements to Humanoid Robots}, year={2008}, booktitle={8th IEEE-RAS International Conference on Humanoid Robots, Workshop Imitation and Coaching in Humanoid Robots}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Humanoids2008b.pdf}, author={Do, Martin and Gehrig, Dirk and Kühne, Hildegard and Azad, Pedram and Pastor, Peter and Asfour, Tamim and Schultz, Tanja and Wörner, Annika and Dillmann, Rüdiger} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1148.php} @inproceedings{laskowski2007modeling, note={MLMI}, title={Modeling Vocal Interaction for Segmentation in Meeting Recognition}, year={2007}, booktitle={4th Joint Workshop on Machine Learning and Multimodal Interaction, Lecture Notes in Computer Science}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/LaskowskiSchultz_MLMI2007.pdf}, author={Laskowski, Kornel and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1153.php} @inproceedings{tam2007correlated, title={Correlated Latent Semantic Model for Unsupervised LM Adaptation}, year={2007}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/TamSchultz_ICASSP2007.pdf}, author={Tam, Yik-Cheung and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1152.php} @inproceedings{jou2007continuous, title={Continuous Electromyographic Speech Recognition with a Multi-Stream Decoding Architecture}, year={2007}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/JouSchultz_ICASSP2007.pdf}, author={Jou, Szu-Chen (Stan) and Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1138.php} @inproceedings{schultz2007spice, title={SPICE: Web-based Tools for Rapid Language Adaptation in Speech Processing Systems}, year={2007}, booktitle={Proceedings of Interspeech}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Schultz_Interspeech2007.pdf}, author={Schultz, Tanja and Black, Alan W and Badaskar, Sameer and Hornyak, Matthew and Kominek, John} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1139.php} @inproceedings{laskowski2007analysis, year={2007}, title={Analysis of the Occurrence of Laughter in Meetings}, booktitle={Proceedings of Interspeech}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/laskowskiINTERSPEECH2007_B.pdf}, author={Laskowski, Kornel and Burger, Susanne} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1143.php} @inproceedings{laskowski2007simultaneous, title={Simultaneous Multispeaker Segmentation for Automatic Meeting Recognition}, year={2007}, booktitle={15th European Signal Processing Conference}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/LASKOWSK_01.pdf}, author={Laskowski, Kornel and Fügen, Christian and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1150.php} @inproceedings{noamany2007advances, title={Advances in the CMU-InterACT Arabic Gale Transcription System}, year={2007}, booktitle={Proceedings of the HLT-NAACL 2007}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/NoamanySchultz_HLT2007.pdf}, author={Noamany, Mohamed and Schaaf, Thomas and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1141.php} @inproceedings{rao2007optimizing, year={2007}, title={Optimizing Sentence Segmentation for Spoken Language Translation}, booktitle={Proceedings of Interspeech}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/RaoSchultz_Interspeech2007.pdf}, author={Rao, Sharath and Lane, Ian and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1142.php} @inproceedings{bach2007handling, title={Handling OOV Words In Arabic ASR Via Flexible Morphological Constraints}, year={2007}, booktitle={Proceedings of Interspeech}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/BachSchultz_Interspeech2007.pdf}, author={Bach, Nguyen and Noamany, Mohamed and Lane, Ian and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1137.php} @inproceedings{wand2007wavelet, title={Wavelet-based Front-End for Electromyographic Speech Recognition}, year={2007}, booktitle={Proceedings of Interspeech}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/WandSchultz_Interspeech2007.pdf}, author={Wand, Michael and Jou, Szu-Chen (Stan) and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1154.php} @inproceedings{stein2007kinematische, year={2007}, title={Kinematische Analyse menschlicher Alltagsbewegungen für die Mensch-Maschine-Interaktion}, booktitle={diverse Workshops 2007}, author={Stein, Thorsten and Fischer, Andreas and Boesnach, Ingo and Gehrig, Dirk and Köhler, Hildegard and Schwameder, Hermann} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1140.php} @inproceedings{tam2007bilingual, year={2007}, title={Bilingual LSA-based Translation Lexicon Adaptation for Spoken Language Translation}, booktitle={Proceedings of Interspeech}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Tam_IS07_LSABasedTranslationLexicon.pdf}, author={Tam, Yik-Cheung and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1136.php} @inproceedings{schultz2007spice, year={2007}, title={SPICE: Web-based Tools for Rapid Language}, booktitle={Adaptation for Speech Processing Systems}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Schultz_Interspeech2007.pdf}, author={Schultz, Tanja and Black, Alan W and Kominek, John and Badaskar, Sameer} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1144.php} @inproceedings{laskowski2007modeling, title={Modeling Vocal Interaction for Text-Independent Classification of Conversation Type}, year={2007}, booktitle={In proceedings of the 8th ISCA/ACL SIGdial Workshop on Discourse and Dialogue}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/laskowskiSIGDIAL2007_B.pdf}, author={Laskowski, Kornel and Ostendorf, Mari and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1151.php} @inproceedings{laskowski2007a, year={2007}, title={A Geometric Interpretation of Non-Target-Normalized Maximum Cross-channel Correlation for Vocal Activity Detection in Meetings}, booktitle={Proceedings of the HLT-NAACL 2007}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/LaskowskiSchultz_HLT2007.pdf}, author={Laskowski, Kornel and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1147.php} @inproceedings{jin2007whispering, note={Multimedia Interaction Human Machine Interface}, title={Whispering Speaker Identification}, year={2007}, booktitle={Proceedings of ICME}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/JinSchultz_ICME2007.pdf}, author={Jin, Qin and Jou, Szu-Chen (Stan) and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1149.php} @inproceedings{tam2007bilingual, year={2007}, title={Bilingual-LSA Based LM Adaptation for Spoken Language Translation}, booktitle={Proceedings of ACL}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/TamSchultz_ACL2007.pdf}, author={Tam, Yik-Cheung and Lane, Ian and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1135.php} @inproceedings{bach2007the, title={The CMU TransTac 2007 Eyes-free and Hands-free Two-way Speech-to-Speech Translation System}, year={2007}, booktitle={International Workshop on Spoken Langage Translation}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/CMU-Transtac-IWSLT2007-camera.pdf}, author={Bach, Nguyen and Eck, Matthias and Charoenpornsawat, Paisarn and Köhler, Thilo and Stüker, Sebastian and Nguyen, ThuyLinh and Hsiao, Roger and Waibel, Alex and Vogel, Stephan and Schultz, Tanja and Black, Alan W} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1146.php} @inproceedings{laskowski2007on, year={2007}, title={On The Correlation Between Perceptual and Contextual Aspects of Laughter}, booktitle={16th International Congress of Phonetic Sciences}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/laskowskiICPhS2007.pdf}, author={Laskowski, Kornel and Burger, Susanne} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1176.php} @inproceedings{black2006speaker, year={2006}, title={Speaker Clustering for Multilingual Synthesis}, booktitle={Proceedings of the ISCA Tutorial and Researc Workshop on Multilingual Speech and Language Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/BlackSchultz_MULTILING2006.pdf}, author={Black, Alan W and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1170.php} @inproceedings{le2006acoustic, title={Acoustic-Phonetic Unit Similarities for Context Dependent Acoustic Model Portability}, year={2006}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/LeSchultz_ICASSP2006.pdf}, author={Le, Viet-Bac and Besacier, Laurent and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1173.php} @inproceedings{schultz2006challenges, title={Challenges with Rapid Adaptation of Speech Translation Systems to New Language Pairs}, year={2006}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SchultzBlack_ICASSP2006.pdf}, author={Schultz, Tanja and Black, Alan W} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1169.php} @inproceedings{jou2006articulatory, year={2006}, title={Articulatory Feature Classification using Surface Electromyography}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/JouSchultz_ICASSP2006.pdf}, author={Jou, Szu-Chen (Stan) and Maier-Hein, Lena and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1171.php} @inproceedings{jin2006far, title={Far-Field Speaker Recognition}, year={2006}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/JinSchultz_ICASSP2006.pdf}, author={Jin, Qin and Pan, Yue and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1172.php} @inproceedings{laskowski2006unsupervised, year={2006}, title={Unsupervised Learning of Overlap Speech Model Parameters for Multichannel Speech Activity Detection in Meetings}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/LaskowskiSchultz_ICASSP2006.pdf}, author={Laskowski, Kornel and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1175.php} @inproceedings{schultz2006rapid, title={Rapid Language Portability of Speech Processing Systems}, year={2006}, booktitle={Invited keynote talk at the ISCA Tutorial and Research Workshop on Multilingual Speech and Language Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/MULTILING2006-Schultz-Spice.pdf}, author={Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1161.php} @inproceedings{tam2006unsupervised, title={Unsupervised Language Model Adaptation Using Latent Semantic Marginals}, year={2006}, booktitle={In proceedings of the 9th ISCA International Conference on Spoken Language Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/TamSchultz_Interspeech2006.pdf}, author={Tam, Yik-Cheung and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1164.php} @inproceedings{jou2006towards, title={Towards Continuous Speech Recognition Using Surface Electromyography}, year={2006}, booktitle={In proceedings of the 9th ISCA International Conference on Spoken Language Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/JouSchultz_Interspeech2006.pdf}, author={Jou, Szu-Chen (Stan) and Schultz, Tanja and Walliczek, Matthias and Kraft, Florian and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1159.php} @inproceedings{charoenpornsawat2006example, year={2006}, title={Example-based Grapheme-to-Phoneme Conversion for Thai}, booktitle={In proceedings of the 9th ISCA International Conference on Spoken Language Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/PaisarnSchultz_Interspeech2006.pdf}, author={Charoenpornsawat, Paisarn and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1160.php} @inproceedings{woszczyna2006spontaneous, year={2006}, title={Spontaneous Thai Speech Recognition}, booktitle={In proceedings of the 9th ISCA International Conference on Spoken Language Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/WoszczynaSchultz_Interspeech2006.pdf}, author={Woszczyna, Monika and Charoenpornsawat, Paisarn and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1163.php} @inproceedings{walliczek2006sub, title={Sub-Word Unit based Non-audible Speech Recognition using Surface Electromyography}, year={2006}, booktitle={In proceedings of the 9th ISCA International Conference on Spoken Language Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/WalliczekSchultz_Interspeech2006.pdf}, author={Walliczek, Matthias and Kraft, Florian and Jou, Szu-Chen (Stan) and Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1156.php} @inproceedings{gehrig2006a, year={2006}, title={A Comparative Study of Gaussian Selection Methods in Large Vocabulary Continuous Speech Recognition}, booktitle={In proceedings of the 9th ISCA International Conference on Spoken Language Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/A_Comparative_Study_of_Gaussian_Selection_Methods_in_Large_Vocabulary_ContinuousSpeech_Recognition.pdf}, author={Gehrig, Dirk and Schaaf, Thomas} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1157.php} @inproceedings{neiberg2006emotion, year={2006}, title={Emotion Recognition in Spontaneous Speech Using GMMs}, booktitle={In proceedings of the 9th ISCA International Conference on Spoken Language Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/is061581.pdf}, author={Neiberg, Daniel and Elenius, Kjell and Laskowski, Kornel} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1158.php} @inproceedings{fügen2006advances, title={Advances in Lecture Recognition: The ISL RT-06S Evaluation System}, year={2006}, booktitle={In proceedings of the 9th ISCA International Conference on Spoken Language Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/is061415.pdf}, author={Fügen, Christian and Wölfel, Matthias and McDonough, John and Ikbal, Shajith and Kraft, Florian and Laskowski, Kornel and Ostendorf, Mari and Stüker, Sebastian} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1165.php} @inproceedings{fügen2006open, year={2006}, title={Open Domain Speech Translation: From Seminars and Speeches to Lectures}, note={JEP}, booktitle={Journies d'E'tude sur la Parole Invited paper and keynote talk}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/FuegenSchultz_JEP2006.pdf}, author={Fügen, Christian and Kolss, Muntsin and Paulik, Matthias and Stüker, Sebastian and Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1155.php} @inproceedings{batliner2006combining, year={2006}, title={Combining Efforts for Improving Automatic Classification of Emotional User States}, booktitle={In proceedings of the 5th Slovenian and 1st International Language Technologies Conference}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/45_Batliner_1of2.pdf}, author={Batliner, Anton and Steidl, Stefan and Schuller, Björn and Seppi, Dino and Laskowski, Kornel and Vogt, Thurid and Devillers, Laurence and Vidrascu, Laurence and Amir, Noam and Kessous, Loic and Aharonson, Vered} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1168.php} @inproceedings{laskowski2006annotation, title={Annotation and Analysis of Emotionally Relevant Behavior in the ISL Meeting Corpus}, year={2006}, booktitle={In proceedings of the 5th ELRA International Conference on Language Resources and Evaluation}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/LREC2006slides.pdf}, author={Laskowski, Kornel and Burger, Susanne} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1174.php} @inproceedings{fügen2006the, title={The ISL RT-06S Speech-to-Text System}, year={2006}, booktitle={Presented at the 3rd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/rt06s-system-description-v10.pdf}, author={Fügen, Christian and Ikbal, Shajith and Kraft, Florian and Kumatani, kenichi and Laskowski, Kornel and McDonough, John and Ostendorf, Mari and Stüker, Sebastian and Wölfel, Matthias} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1166.php} @inproceedings{neiberg2006emotion, title={Emotion Recognition in Spontaneous Speech}, year={2006}, booktitle={In proceedings of the 19th Swedish Phonetics Conference}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/neiberg_et_al_fon06.pdf}, author={Neiberg, Daniel and Elenius, Kjell and Karlsson, Inger and Laskowski, Kornel} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1167.php} @inproceedings{charoenpornsawat2006thai, year={2006}, title={Thai Grapheme-Based Speech Recognition}, booktitle={Human Language Technology Conference}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/CharoenpornsawatSchultz_HLT2006.pdf}, author={Charoenpornsawat, Paisarn and Hewavitharana, Sanjika and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1177.php} @inproceedings{stelzner2006a, title={A large-scale database of human movements to humanize robot motion}, year={2006}, booktitle={French-German Workshop on Humanoid and Legged Robots, HLR 2006}, author={Stelzner, Günther and Simonids, Christian and Boesnach, Ingo and Köhler, Hildegard and Gehrig, Dirk and Stein, Thorsten and Fischer, Andreas} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1185.php} @inproceedings{jou2005whispery, year={2005}, title={Whispery Speech Recognition using Adapted Articulatory Features}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/JouSchultz_ICASSP05.pdf}, author={Jou, Szu-Chen (Stan) and Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1184.php} @inproceedings{suebvisai2005thai, title={Thai Automatic Speech Recognition}, year={2005}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SuebvisaiSchultz_ICASSP05.pdf}, author={Suebvisai, Sinaporn and Charoenpornsawat, Paisarn and Black, Alan W and Woszczyna, Monika and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1186.php} @inproceedings{honal2005automatic, year={2005}, title={Automatic Disfluency Removal on Recognized Spontaneous Speech - Rapid Adaptation to Speaker-Dependent Disfluencies}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/HonalSchultz_ICASSP05.pdf}, author={Honal, Matthias and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1182.php} @inproceedings{tam2005dynamic, year={2005}, title={Dynamic Language Model Adaptation using Variational Bayes Inference}, booktitle={Proceedings of the Eurospeech}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/TamSchultz_Eurospeech2005.pdf}, author={Tam, Yik-Cheung and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1183.php} @inproceedings{paulik2005document, title={Document Driven Machine Translation Enhanced Automatic Speech Recognition}, year={2005}, booktitle={Proceedings of the Eurospeech}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/PaulikSchultz_Eurospeech2005.pdf}, author={Paulik, Matthias and Fügen, Christian and Schaaf, Thomas and Schultz, Tanja and Stüker, Sebastian and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1498.php} @inproceedings{maier-hein2005session, year={2005}, title={Session Independent Non-Audible Speech Recognition Using Surface Electromyography}, booktitle={Proceedings of the Automatic Speech Recognition and Understanding Workshop}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Maier-HeinSchultz_ASRU2005.pdf}, author={Maier-Hein, Lena and Metze, Florian and Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1496.php} @inproceedings{paulik2005speech, title={Speech Translation Enhanced Automatic Speech Recognition}, year={2005}, booktitle={Proceedings of the Automatic Speech Recognition and Understanding Workshop}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/PaulikSchultz_ASRU2005.pdf}, author={Paulik, Matthias and Stüker, Sebastian and Fügen, Christian and Schultz, Tanja and Schaaf, Thomas and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1181.php} @inproceedings{honal2005identifying, year={2005}, title={Identifying User State using Electroencephalographic Data}, booktitle={Proceedings of the International Conference on Multimodal Input}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/HonalSchultz_ICMI2005.pdf}, author={Honal, Matthias and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1180.php} @inproceedings{engelbrecht2005rapid, title={Rapid Development of an Afrikaans-English Speech-to-Speech Translator}, year={2005}, booktitle={Proceedings of International Workshop of Spoken Language Translation}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/EngelbrechtSchultz_IWSLT2005.pdf}, author={Engelbrecht, Herman and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1198.php} @inproceedings{kirchhoff2004icassp, title={ICASSP 2004, Special Session on Multilinguality in Speech Processing}, year={2004}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing}, author={Kirchhoff, Katrin and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1192.php} @inproceedings{jin2004speaker, year={2004}, title={Speaker Segmentation and Clustering in Meetings}, booktitle={International Conference of Spoken Language Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SchultzJin_icslp04.pdf}, author={Jin, Qin and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1191.php} @inproceedings{metze2004issues, year={2004}, title={Issues in Meeting Transcription - The ISL Meeting Transcription System}, booktitle={International Conference of Spoken Language Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SchultzMetze_icslp04.pdf}, author={Metze, Florian and Jin, Qin and Fügen, Christian and Laskowski, Kornel and Pan, Yue and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1195.php} @inproceedings{stüker2004a, title={A Grapheme based Speech Recognition System for Russian}, year={2004}, booktitle={SPECOM Speech and Computer}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SchultzStueker_SPECOM04.pdf}, author={Stüker, Sebastian and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1187.php} @inproceedings{schultz2004towards, title={Towards Rapid Language Portability of Speech Processing Systems}, year={2004}, booktitle={Conference on Speech and Language Systems for Human Communication}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Schultz_SPLASH04.pdf}, author={Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1200.php} @inproceedings{jin2004speaker, year={2004}, title={Speaker Segmentation and Clustering in Meetings}, booktitle={NIST Meeting Recognition Workshop}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SchultzJin_NIST04.pdf}, author={Jin, Qin and Laskowski, Kornel and Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1188.php} @inproceedings{yu2004the, year={2004}, title={The ISL RT04 Mandarin Broadcast News Evaluation System}, booktitle={EARS Rich Transcription Workshop}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SchultzYu_EARS04.pdf}, author={Yu, Hua and Tam, Yik-Cheung and Schaaf, Thomas and Stüker, Sebastian and Jin, Qin and Noamany, Mohamed and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1197.php} @inproceedings{waibel2004towards, title={Towards Language Portability in Statistical Machine Translation}, year={2004}, booktitle={Invited paper, Special Session on Multilinguality in Speech Processing, Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SchultzWaibel_icassp04.pdf}, author={Waibel, Alex and Schultz, Tanja and Vogel, Stephan and Fügen, Christian and Honal, Matthias and Kolss, Muntsin and Reichert, Jürgen and Stüker, Sebastian} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1193.php} @inproceedings{jou2004adaptation, title={Adaptation for Soft Whisper Recognition Using a Throat Microphone}, year={2004}, booktitle={International Conference of Spoken Language Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SchultzJou_icslp04.pdf}, author={Jou, Szu-Chen (Stan) and Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1194.php} @inproceedings{saleem2004using, title={Using Word Lattice Information for a Tighter Coupling in Speech Translation Systems}, year={2004}, booktitle={International Conference of Spoken Language Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SchultzSaleem_icslp04.pdf}, author={Saleem, Shirin and Jou, Szu-Chen (Stan) and Vogel, Stephan and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1196.php} @inproceedings{mimer2004graphembasierte, title={Graphembasierte Spracherkennung unter Verwendung flexibler Entscheidungsbäume}, year={2004}, booktitle={Elektronische Sprachsignalverarbeitung ESSV}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SchultzMimer_ESSV04.pdf}, author={Mimer, Borislava and Stüker, Sebastian and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1199.php} @inproceedings{metze2004issues, title={Issues in Meeting Transcription - The ISL Meeting Transcription System}, year={2004}, booktitle={NIST Meeting Recognition Workshop}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SchultzMetze_NIST04.pdf}, author={Metze, Florian and Fügen, Christian and Pan, Yue and Schultz, Tanja and Yu, Hua} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1189.php} @inproceedings{katzenmaier2004human, year={2004}, title={Human-Human-Robot Interaction}, booktitle={International Conference on Multimodal Interfaces}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SchultzKatzenmaier_icmi04.pdf}, author={Katzenmaier, Michael and Schultz, Tanja and Stiefelhagen, Rainer} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1190.php} @inproceedings{laskowski2004crosscorrelation, title={Crosscorrelation-based Multispeaker Speech Activity Detection}, year={2004}, booktitle={International Conference of Spoken Language Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/SchultzLaskowski_icslp04.pdf}, author={Laskowski, Kornel and Jin, Qin and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1201.php} @inproceedings{schultz2004a, year={2004}, title={A Thai Speech Translation System For Medical Dialogs}, booktitle={Proceedings of the Human Language Technologies}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/HLT04-Schultz.pdf}, author={Schultz, Tanja and Alexander, Dorcas and Black, Alan W and Peterson, Kay and Suebvisai, Sinaporn and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1208.php} @inproceedings{stüker2003integrating, year={2003}, title={Integrating Multilingual Articulatory Features into Speech Recognition}, booktitle={Proceedings of the 8th European Conference on Speech Communication and Technology}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Euro03-StuekerSchultz.pdf}, author={Stüker, Sebastian and Metze, Florian and Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1212.php} @inproceedings{waibel2003smart, title={SMaRT: The Smart Meeting Room Task at ISL}, year={2003}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ICASSP03-schultz.pdf}, author={Waibel, Alex and Schultz, Tanja and Bett, Michael and Malkin, Robert and Rogina, Ivica and Stiefelhagen, Rainer and Yang, Jie} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1204.php} @inproceedings{wang2003non, title={Non-Native Spontaneous Speech Recognition through Polyphone Decisision Tress Specialization}, year={2003}, booktitle={Proceedings of the 8th European Conference on Speech Communication and Technology}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Euro03-WangSchultz.pdf}, author={Wang, Zhirong and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1203.php} @inproceedings{waibel2003speechalator, title={Speechalator: two-way speech-to-speech translation on a consumer PDA}, year={2003}, booktitle={Proceedings of the 8th European Conference on Speech Communication and Technology}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Euro03-BlackSchultz.pdf}, author={Waibel, Alex and Badran, Ahmed and Black, Alan W and Frederking, Robert and Gates, Donna and Lavie, Alon and Levin, Lori and Lenzo, Kevin and Tomokiyo-Mayfield, Laura and Reichert, Jürgen and Schultz, Tanja and Wallace, Dorcas and Woszczyna, Monika and Zhang, Jing} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1205.php} @inproceedings{yu2003enhanced, year={2003}, title={Enhanced Tree Clustering with Single Pronunciation Dictionary for Conversational Speech Recognition}, booktitle={Proceedings of the 8th European Conference on Speech Communication and Technology}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Euro03-YuSchultz.pdf}, author={Yu, Hua and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1206.php} @inproceedings{honal2003correction, year={2003}, title={Correction of Disfluencies in Spontaneous Speech using a Noisy-Channel Approach}, booktitle={Proceedings of the 8th European Conference on Speech Communication and Technology}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Euro03-HonalSchultz.pdf}, author={Honal, Matthias and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1213.php} @inproceedings{wang2003comparison, title={Comparison of Acoustic Model Adaptation Techniques}, year={2003}, booktitle={Non-native Speech}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ICASSP03-wang.pdf}, author={Wang, Zhirong and Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1210.php} @inproceedings{yu2003implicit, title={Implicit Trajectory Modeling through Gaussian Transition Models}, year={2003}, booktitle={Human Language Technology & North American Chapter of the Association for Computational Linguistics}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/HLT03-YuSchultz.pdf}, author={Yu, Hua and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1207.php} @inproceedings{killer2003grapheme, year={2003}, title={Grapheme based Speech Recognition}, booktitle={Proceedings of the 8th European Conference on Speech Communication and Technology}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Euro03-KillerSchultz.pdf}, author={Killer, Mirjam and Stüker, Sebastian and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1211.php} @inproceedings{stüker2003multilingual, year={2003}, title={Multilingual Articulatory Features}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ICASSP03-stueker.pdf}, author={Stüker, Sebastian and Schultz, Tanja and Metze, Florian and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1209.php} @inproceedings{waibel2003speechalator, year={2003}, title={Speechalator: Two-way Speech-to-Speech Translation in your Hand}, booktitle={Human Language Technology & North American Chapter of the Association for Computational Linguistics}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/HLT03-WaibelSchultz.pdf}, author={Waibel, Alex and Badran, Ahmed and Black, Alan W and Frederking, Robert and Gates, Donna and Lavie, Alon and Levin, Lori and Lenzo, Kevin and Tomokiyo-Mayfield, Laura and Reichert, Jürgen and Schultz, Tanja and Wallace, Dorcas and Woszczyna, Monika and Zhang, Jing} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1202.php} @inproceedings{fügen2003efficient, year={2003}, title={Efficient Handling of Multilingual Language Models}, booktitle={Proceedings of the Workshop of Automatic Speech Recognition Understanding}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Asru03-FuegenSchultz.pdf}, author={Fügen, Christian and Stüker, Sebastian and Soltau, Hagen and Metze, Florian and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1219.php} @inproceedings{schultz2002improvements, year={2002}, title={Improvements in Non-verbal Cue Identification using Multilingual Phone Strings}, booktitle={Proceedings of the Speech-to-Speech Translation Workshop on the 40th Anniversary Meeting of the Association for Computational Linguistics}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_ACL2002.pdf}, author={Schultz, Tanja and Jin, Qin and Laskowski, Kornel and Tribble, Alicia and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1218.php} @inproceedings{lavie2002a, title={A Multi-Perspective Evaluation of the NESPOLE! Speech-to-Speech Translation System}, year={2002}, booktitle={Proceedings of the Speech-to-Speech Translation Workshop on the 40th Anniversary Meeting of the Association for Computational Linguistics}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/s2s013.pdf}, author={Lavie, Alon and Metze, Florian and Cattoni, Roldano and Constantini, Erica} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1216.php} @inproceedings{schultz2002globalphone, title={GlobalPhone: A Multilingual Speech and Text Database developed at Karlsruhe University}, year={2002}, booktitle={Proceedings of the International Conference of Spoken Language Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_icslp02.pdf}, author={Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1224.php} @inproceedings{schultz2002speaker, year={2002}, title={Speaker, Accent, and Language Identification using Multilingual Phone Strings}, booktitle={Proceedings of the Human Language Technology Meeting}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_hlt2002.pdf}, author={Schultz, Tanja and Jin, Qin and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1220.php} @inproceedings{zhao2002towards, year={2002}, title={Towards Robust Parametric Segmental Trajectory Model for Vowel Recognition}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ICASSP02-bzhao.pdf}, author={Zhao, Bing and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1223.php} @inproceedings{metze2002the, title={The NESPOLE! Speech-to-Speech Translation System}, year={2002}, booktitle={Proceedings of the Human Language Technology Meeting}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/lavie-hlt02demo.pdf}, author={Metze, Florian and McDonough, John and Soltau, Hagen and Langley, Chad and Lavie, Alon and Schultz, Tanja and Waibel, Alex and Cattoni, Roldano and Lazzari, Gianni and Pianesi, Fabio} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1222.php} @inproceedings{metze2002enhancing, title={Enhancing the Usability and Performance of NESPOLE!: a Real-World Speech-to-Speech Translation System}, year={2002}, booktitle={Proceedings of the Human Language Technology Meeting}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/lavie-hlt02poster.pdf}, author={Metze, Florian and McDonough, John and Soltau, Hagen and Lavie, Alon and Levin, Lori and Langley, Chad and Schultz, Tanja and Waibel, Alex and Cattoni, Roldano and Lazzari, Gianni and Mana, Nadia and Pianesi, Fabio and Pianta, Emanuelle} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1215.php} @inproceedings{wang2002towards, year={2002}, title={Towards Universal Speech Recognition}, booktitle={Proceedings of the International Conference on Multimodal Interfaces}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ICMI02-Wang.pdf}, author={Wang, Zhirong and Topkara, Umut and Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1217.php} @inproceedings{jin2002phonetic, title={Phonetic Speaker Identification}, year={2002}, booktitle={Proceedings of the International Conference of Spoken Language Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ICSLP02-qjin.pdf}, author={Jin, Qin and Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1231.php} @inproceedings{fügen2001lingwear, year={2001}, title={LingWear: A Mobil Tourist Information System}, booktitle={Proceedings of the Human Language Technology Meeting}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/fuegen_hlt01-final.pdf}, author={Fügen, Christian and Westphal, Martin and Schneider, Mike and Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1229.php} @inproceedings{lavie2001domain, year={2001}, title={Domain Portability in Speech-to-Speech Translation}, booktitle={Proceedings of the Human Language Technology Meeting}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/levin_hlt01-final.pdf}, author={Lavie, Alon and Levin, Lori and Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1230.php} @inproceedings{waibel2001advances, year={2001}, title={Advances in Meeting Recognition}, booktitle={Proceedings of the Human Language Technology Meeting}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_hlt01-notebook.pdf}, author={Waibel, Alex and Yu, Hua and Soltau, Hagen and Schultz, Tanja and Schaaf, Thomas and Pan, Yue and Metze, Florian and Bett, Michael} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1228.php} @inproceedings{schultz2001the, year={2001}, title={The ISL Meeting Room System}, booktitle={Proceedings of the Workshop on Hands-Free Speech Communication}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_hsc01.ps.gz}, author={Schultz, Tanja and Waibel, Alex and Bett, Michael and Metze, Florian and Pan, Yue and Ries, Klaus and Schaaf, Thomas and Soltau, Hagen and Yu, Hua and Zechner, Klaus} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1227.php} @inproceedings{waibel2001advances, year={2001}, title={Advances in Automatic Meeting Record Creation and Access}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_icassp01.pdf}, author={Waibel, Alex and Bett, Michael and Ries, Klaus and Schaaf, Thomas and Schultz, Tanja and Soltau, Hagen and Yu, Hua and Zechner, Klaus} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1226.php} @inproceedings{schultz2001experiments, year={2001}, title={Experiments on Cross-language Acoustic Modeling}, booktitle={Proceedings of the 7th European Conference on Speech Communication and Technology}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_euro01.pdf}, author={Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1225.php} @inproceedings{kunzmann2001portability, title={Portability of Automatic Speech Recognition Technology to New Languages: Multilinguality Issues and Speech/Text Resources}, year={2001}, booktitle={Panel Session on Automatic Speech Recognition and Understanding}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/asru2001.ppt}, author={Kunzmann, Jimmy and Choukri, Khalid and Jahnke, Eric and Kiessling, Andreas and Knill, Kate and Lamel, Lori and Schultz, Tanja and Yamamoto, Seiichi} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1236.php} @inproceedings{schultz2000polyphone, title={Polyphone Decision Tree Specialization for Language Adaptation}, year={2000}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_icassp00-multi.pdf}, author={Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1234.php} @inproceedings{Çarki2000turkish, title={Turkish LVCSR: Towards better Speech Recognition for Agglutinative Languages}, year={2000}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_icassp00-tu.pdf}, author={Çarki, Kenan and Geutner, Petra and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1235.php} @inproceedings{metze2000confidence, title={Confidence Measure based Language Identification}, year={2000}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_icassp00-lid.pdf}, author={Metze, Florian and Kemp, Thomas and Schaaf, Thomas and Schultz, Tanja and Soltau, Hagen} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1232.php} @inproceedings{kurematsu2000verbmobil, title={Verbmobil Dialogues: Multifaced Analysis}, year={2000}, booktitle={Proceedings of the International Conference of Spoken Language Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/kurematsu_icslp2000.pdf}, author={Kurematsu, Akira and Akegami, Youichi and Burger, Susanne and Jekat, Susanne and Lause, Brigitte and MacLaren, Victoria and Oppermann, Daniela and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1095.php} @inproceedings{li2000the, year={2000}, title={The I4U System in NIST 2008 Speaker Recognition Evaluation}, booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/LiSchultz-ICASSP2009.pdf}, author={Li, Haizhou and Ma, Bin and Lee, K-A. and Sun, Hanwu and Zhu, Donglai and Sim, Khe Chai and You, Changhuai and Tong, Rong and Karkkainen, Ismo and Huang, Chien-Lin and Pervouchine, Vladimir and Guo, Wu and Li, Yijie and Dai, Lirong and Nosratighods, M. and Tharmarajah, T. and Epps, Julien and Ambikairajah, E. and Chng, E.-S. and Jin, Qin and Schultz, Tanja} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1233.php} @inproceedings{schultz2000language, title={Language Portability in Acoustic Modeling}, year={2000}, pages={59-64}, booktitle={Proceedings of the Workshop on Multilingual Speech Communication}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_msc00.pdf}, author={Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1237.php} @inproceedings{schultz1999language, title={Language adaptive LVCSR through Polyphone Decision Tree Specialization}, pages={85-90}, year={1999}, booktitle={Workshop on Multi-lingual Interoperability in Speech Technology}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_mist99.pdf.zip}, author={Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1238.php} @inproceedings{reichert1999mandarin, pages={815-818}, year={1999}, title={Mandarin Large Vocabulary Speech Recognition using the GlobalPhone Database}, booktitle={Proceedings of the 6th European Conference on Speech Communication and Technology}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/EUROSPEECH99-reichert.pdf}, author={Reichert, Jürgen and Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1240.php} @inproceedings{kurematsu1999development, year={1999}, title={Development of Data Collection and Transliteration of Japanese Spontaneous Database in the Travel Arrangement Task Domain}, booktitle={International Workshop on East-Asien Language Resources and Evaluation}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/kurematsu_cocosda99.pdf}, author={Kurematsu, Akira and Akegami, Youichi and Schultz, Tanja and Burger, Susanne} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1241.php} @inproceedings{schultz1999experiments, title={Experiments towards a Multi-language LVCSR Interface}, year={1999}, booktitle={2nd International Conference on Multi-modal Interfaces}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_icmi99.ps.gz}, author={Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1239.php} @inproceedings{kiecza1999data, title={Data-Driven Determination of Appropriate Dictionary Units for Korean LVCSR}, pages={323-327}, year={1999}, booktitle={1999 Proceedings of the International Conference on Speech Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_icsp99.pdf.zip}, author={Kiecza, Daniel and Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1243.php} @inproceedings{schultz1998language, title={Language Independent and Language Adaptive Large Vocabulary Speech Recognition}, pages={1819--1822}, year={1998}, booktitle={Proceedings of the International Conference of Spoken Language Processing , Vol. 5}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_icslp98.pdf.zip}, author={Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1242.php} @inproceedings{westphal1998linear, title={Linear Discriminant - A New Criterion for Speaker Normalization}, year={1998}, pages={1819--1822}, booktitle={Proceedings of the International Conference of Spoken Language Processing , Vol. 5}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ICSLP98-west.pdf.zip}, author={Westphal, Martin and Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1245.php} @inproceedings{schultz1998adaptation, pages={207-210}, year={1998}, title={Adaptation of Pronunciation Dictionaries for Recognition of Unseen Languages}, booktitle={Workshop on Speech and Communication}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_specom98.pdf.zip}, author={Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1248.php} @inproceedings{soltau1998recognition, year={1998}, title={Recognition of Music Types}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ICASSP98-hagen.pdf.zip}, author={Soltau, Hagen and Schultz, Tanja and Westphal, Martin and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1249.php} @inproceedings{schultz1998multilingual, pages={259-262}, year={1998}, title={Multilingual and Crosslingual Speech Recognition}, booktitle={Proceedings of the DARPA Broadcast News Transcription and Understanding}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_darpa98.pdf.zip}, author={Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1247.php} @inproceedings{schultz1998development, title={Development of Multilingual Acoustic Models in the GlobalPhone Project}, pages={311-316}, year={1998}, booktitle={Proceedings of the 1st Workshop on Text, Speech, and Dialogue, ; TSD}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_tsd98.pdf.zip}, author={Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1246.php} @inproceedings{schultz1998das, year={1998}, title={Das Projekt GlobalPhone: Multilinguale Spracherkennung}, booktitle={Computers, Linguistics, and Phonetics between Language and Speech. Proceedings of the 4th Conference on NLP}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_konvens98.pdf.zip}, author={Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1250.php} @inproceedings{schultz1997japanese, year={1997}, pages={371--373}, title={Japanese LVCSR on the Spontaneous Scheduling Task with JANUS-3}, booktitle={Proceedings of the 5th European Conference on Speech Communication and Technology, Vol. 1}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_euro97_jsst.pdf.zip}, author={Schultz, Tanja and Koll, Detlef and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1251.php} @inproceedings{schultz1997fast, pages={371--373}, year={1997}, title={Fast Bootstrapping of LVCSR Systems with Multilingual Phoneme Sets}, booktitle={Proceedings of the 5th European Conference on Speech Communication and Technology, Vol. 1}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_euro97_gp.pdf.zip}, author={Schultz, Tanja and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1252.php} @inproceedings{schultz1997the, title={The GlobalPhone Project: Multilingual LVCSR with JANUS-3}, year={1997}, pages={20--27}, booktitle={Multilingual Information Retrieval Dialogs: 2nd SQEL Workshop}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_sqel97.pdf.zip}, author={Schultz, Tanja and Westphal, Martin and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1254.php} @inproceedings{schultz1996lvcsr, title={LVCSR-based Language Identification}, pages={781-784}, year={1996}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_icassp96.pdf.zip}, author={Schultz, Tanja and Rogina, Ivica and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1253.php} @inproceedings{schultz1996automatische, title={Automatische Identifizierung spontan gesprochener Sprachen mit neuronalen Netzen}, year={1996}, pages={102--110}, booktitle={Proceedings of the 3rd Conference on Natural Language Processing and Speech Technology}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_konvens96.pdf.zip}, author={Schultz, Tanja and Soltau, Hagen} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1256.php} @inproceedings{schultz1995experiments, year={1995}, pages={89--94}, title={Experiments with LVCSR based Language Identification}, booktitle={Proceedings of the Speech Research Symposium SRS XV}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_srs95.pdf.zip}, author={Schultz, Tanja and Rogina, Ivica and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1257.php} @inproceedings{schultz1995acoustic, title={Acoustic and Language Modeling of Human and Nonhuman Noises for Human-to-Human Spontaneous Speech Recognition}, pages={293--296}, year={1995}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol. 1}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_icassp95.pdf.zip}, author={Schultz, Tanja and Rogina, Ivica} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1255.php} @inproceedings{suhm1995janus, title={JANUS: Towards Multilingual Spoken Language Translation}, pages={185-189}, year={1995}, booktitle={ARPA Workshop on Speech and Natural Language Technology}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/suhm_slt95.pdf}, author={Suhm, B and Geutner, Petra and Kemp, Thomas and Lavie, Alon and Tomokiyo-Mayfield, Laura and McNair, A.E and Rogina, Ivica and Schultz, Tanja and Sloboda, T and Ward, W and Woszczyna, Monika and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/konferenzen_1258.php} @inproceedings{woszczyna1994towards, pages={345--348}, year={1994}, title={Towards Spontaneous Speech Translation}, booktitle={Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol. 1}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ICASSP94.janus.pdf}, author={Woszczyna, Monika and Aoki-Waibel, N and Buø, F.D and Coccaro, N and Horiguchi, K and Kemp, Thomas and Lavie, Alon and McNair, A.E and Polzin, T and Rogina, Ivica and Rose, C.P and Schultz, Tanja and Suhm, B and Tomita, M and Waibel, Alex} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2897.php} @bachelorsthesis{selvanayagam2014modellierung, school={Karlsruher Institut für Technologie}, title={Modellierung der Dauer von HMM Zuständen für multilinguale Spracherkennung}, year={2014}, supervisor={Telaar, Dominic and Schultz, Tanja}, author={Selvanayagam, Kopiga} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2896.php} @bachelorsthesis{deßloch2014spoken, school={Karlsruher Institut für Technologie}, title={Spoken Term Detection using Deep Neural Networks}, year={2014}, supervisor={Telaar, Dominic and Vu, Thang and Schultz, Tanja}, author={Deßloch, Florian} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2863.php} @bachelorsthesis{dinh2014fundamental, school={Karlsruher Institut für Technologie}, title={Fundamental Frequency Analysis and Generation for Whispered to Audible Speech Conversion}, year={2014}, supervisor={Janke, Matthias and Schultz, Tanja}, author={Dinh, Martin} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2837.php} @bachelorsthesis{onogur2014hierarchische, school={Karlsruher Institut für Technologie}, year={2014}, title={Hierarchische Diskriminierung von visuellem und auditivem Aufmerksamkeitsfokus durch Ereigniskorrelierte Potentiale}, supervisor={Heger, Dominik}, author={Onogur, Sinan} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2786.php} @bachelorsthesis{becker2014adaption, school={Karlsruher Institut für Technologie}, title={Adaption of a Cognitive Decision-Making Model through the Application of Workload Recognition}, year={2014}, supervisor={Putze, Felix}, author={Becker, Vincent} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2727.php} @bachelorsthesis{leidig2014single, school={Karlsruher Institut für Technologie}, year={2014}, title={Single and Combined Features for the Detection of Anglicisms in German and Afrikaans}, supervisor={Schlippe, Tim and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/BA_SebastianLeidig.pdf}, author={Leidig, Sebastian} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2826.php} @bachelorsthesis{röhrs2013kalman, school={Karlsruher Institut für Technologie}, title={Kalman Filter zur Bestimmung der Blickrichtung durch EOG}, year={2013}, supervisor={Herff, Christian}, author={Röhrs, Eike Simon} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2802.php} @bachelorsthesis{sazinger2013entwicklung, school={Karlsruher Institut für Technologie}, year={2013}, title={Entwicklung und Evaluation von Benutzerschnittstellen zur Unterstützung bei einer komplexen Aufgabe unter verschiedenen Workload-Bedingungen}, supervisor={Putze, Felix and Schultz, Tanja}, author={Sazinger, Matthias} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2801.php} @bachelorsthesis{klinowski2013designing, school={Karlsruher Institut für Technologie}, year={2013}, title={Designing a workload adaptive dialog system with flexible initiative}, supervisor={Putze, Felix and Schultz, Tanja}, author={Klinowski, Patrick} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2800.php} @bachelorsthesis{axtmann2013online, school={Karlsruher Institut für Technologie}, year={2013}, title={Online detection of error related potentials using electroencephalography and spatial filtering}, supervisor={Putze, Felix and Schultz, Tanja}, author={Axtmann, Michael} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2798.php} @bachelorsthesis{stefano2013classification, school={Karlsruher Institut für Technologie}, title={Classification of perceptual modality and processing code in multimodal cognition processes using EEG}, year={2013}, supervisor={Putze, Felix and Schultz, Tanja}, author={Stefano, Antonino Simone Di} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2799.php} @bachelorsthesis{katev2013comparison, school={Karlsruher Institut für Technologie}, title={Comparison of individualized Reinforcement Learning models with real-life subjects for a complex learning task}, year={2013}, supervisor={Putze, Felix and Schultz, Tanja}, author={Katev, Kalin} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2784.php} @bachelorsthesis{adigüzel2013signalinterpolation, school={Karlsruher Institut für Technologie}, title={Signalinterpolation für Elektrodenarrays in der EMG-basierten Spracherkennung}, year={2013}, supervisor={Wand, Michael and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/BA-Adiguezel.pdf}, author={Adigüzel, Davud} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2459.php} @bachelorsthesis{vogel2013kontextsensitive, school={Karlsruher Institut für Technologie}, year={2013}, title={Kontextsensitive Konvertierung von geflüsterter auf hörbare Sprache: Implementierung und Evaluation}, supervisor={Wand, Michael and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/BA_MaximilianVogel.pdf}, author={Vogel, Maximilian} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2427.php} @bachelorsthesis{yurchenko2013cross, school={Karlsruher Institut für Technologie}, title={Cross-Lingual Pronunciation Dictionary Production}, year={2013}, supervisor={Schlippe, Tim and Schultz, Tanja}, author={Yurchenko, Kateryna} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2289.php} @bachelorsthesis{himmelsbach2013rauschunterdr, school={Karlsruher Institut für Technologie}, title={Rauschunterdrückung durch Quellenseparation in der EMG-basierten Spracherkennung}, year={2013}, supervisor={Wand, Michael and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/BA_Adam_Himmelsbach.pdf}, author={Himmelsbach, Adam} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2193.php} @bachelorsthesis{heistermann2013decomposition, school={Karlsruher Institut für Technologie}, title={Decomposition of Multichannel Electromyographic Signals for a Silent Speech Interface}, year={2013}, supervisor={Janke, Matthias and Wand, Michael and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/BA_Till_Heistermann.pdf}, author={Heistermann, Till} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2815.php} @bachelorsthesis{ernst2012bootstrapping, school={Karlsruher Institut für Technologie}, title={Bootstrapping Pronunciation Dictionaries with Multilingual Phoneme Recognition}, year={2012}, supervisor={Schlippe, Tim and Vu, Ngoc Thang and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/BA-DarioErnst.pdf}, author={Ernst, Dario} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2805.php} @bachelorsthesis{meyer2012kognitive, school={Karlsruher Institut für Technologie}, year={2012}, title={Kognitive Modellierung komplexer strategischer Entscheidungsprozesse mittels EEG und Reinforcement Learning}, supervisor={Putze, Felix and Schultz, Tanja}, author={Meyer, Johannes and Borné, Joscha} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2804.php} @bachelorsthesis{bechberger2012modeling, school={Karlsruher Institut für Technologie}, year={2012}, title={Modeling human memory performance under influence of cognitive workload}, supervisor={Putze, Felix and Schultz, Tanja}, author={Bechberger, Lucas} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2803.php} @bachelorsthesis{siem2012transfer, school={Karlsruher Institut für Technologie}, year={2012}, title={Transfer entropy for extracranial EEG analysis with TRENTOOL in a visual cued motor task}, supervisor={Putze, Felix and Schultz, Tanja}, author={Siem, Sebastian Mendez} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2355.php} @bachelorsthesis{erhardt2012error, school={Karlsruher Institut für Technologie}, year={2012}, title={Error Blaming based on Decoding Output}, supervisor={Telaar, Dominic and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ba_mark_erhardt.pdf}, author={Erhardt, Mark} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2115.php} @bachelorsthesis{weiner2012integrating, school={Karlsruher Institut für Technologie}, year={2012}, title={Integrating Language ID into Code-Switch Speech Recognition}, supervisor={Vu, Ngoc Thang and Telaar, Dominic and Metze, Florian and Schultz, Tanja}, author={Weiner, Jochen} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_1974.php} @bachelorsthesis{alexandrov2012f, school={Karlsruher Institut für Technologie}, year={2012}, title={F0-Erkennung bei elektromyographischer Sprachsynthese mit Elektrodenarrays}, supervisor={Janke, Matthias and Wand, Michael and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/BA_Luben_Alexandrov.pdf}, author={Alexandrov, Luben} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2806.php} @bachelorsthesis{colling2011appraisal, school={Karlsruher Institut für Technologie}, year={2011}, title={Appraisal-basierte Modellierung von Emotionen in der Interaktion mit einem virtuellen Beifahrer}, supervisor={Putze, Felix and Schultz, Tanja}, author={Colling, Steven} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2369.php} @bachelorsthesis{kirzner2011analyse, school={Karlsruher Institut für Technologie}, year={2011}, title={Analyse und Klassifikation von EEG und EMG bei lauter und lautloser Sprache}, supervisor={Heger, Dominic and Wand, Michael and Schultz, Tanja}, author={Kirzner, Evgheni} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2044.php} @bachelorsthesis{stahlberg2011discovering, school={Karlsruher Institut für Technologie}, title={Discovering Vocabulary of a Language through Cross-Lingual Alignment}, year={2011}, supervisor={Schlippe, Tim and Vogel, Stephan and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/BA_FelixStahlberg_Ausarbeitung.pdf}, author={Stahlberg, Felix} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_1643.php} @bachelorsthesis{schulte2011aufbau, school={Karlsruher Institut für Technologie}, title={Aufbau eines EMG-basierten Spracherkennungssystems unter Verwendung von Elektrodenarrays}, year={2011}, supervisor={Wand, Michael and Janke, Matthias and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/BA-Schulte.pdf}, author={Schulte, Christopher} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_1954.php} @bachelorsthesis{werfel2011integration, school={Karlsruher Institut für Technologie}, title={Integration von Objektwissen in die automatische Erkennung menschlicher Bewegungen}, year={2011}, supervisor={Schultz, Tanja and Gehrig, Dirk}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/BachelorarbeitWerfel.pdf}, author={Werfel, Sergej} } @comment{Old page: http://csl.anthropomatik.kit.edu/1853_2061.php} @bachelorsthesis{jabbar2010erfassung, school={Karlsruher Institut für Technologie}, year={2010}, title={Erfassung und Analyse von Bewegungssequenzen mittels Inertialsensorik}, supervisor={Schultz, Tanja}, author={Jabbar, Jalil Amir} } @bachelorsthesis{mai20l9segmentation, school={Universität Bremen}, year={2019}, title={Automatische Segmentierung von Bewegungsdaten eines biosignalbasierten, in einer Kniebandage integrierten HAR Systems}, supervisor={Liu, Hui and Schultz, Tanja and Frese, Udo}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/BA_Mai_2019.pdf}, author={Mai, Lennnard} } @bachelorsthesis{hartmann2019har, school={Universität Bremen}, year={2019}, title={Implementation and Optimisation of a Human Activity Recognition System using Sensors integrated into a Knee Bandage}, supervisor={Liu, Hui and Schultz, Tanja and Jarke, Juliane}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/BA_Hartmann_2019.pdf}, author={Hartmann, Yale} } @bachelorsthesis{lahrberg2021crosschannel, school={Universität Bremen}, year={2021}, title={Direction Distinguishment in Wearable Sensor-Based Human Activity Recognition Using Cross-Channel Features}, supervisor={Liu, Hui and Hartmann, Yale and Schultz, Tanja and Röfer, Thomas}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/BA_Lahrberg_2021.pdf}, author={Lahrberg, Steffen} } @bachelorsthesis{urban2021app, school={Universität Bremen}, year={2019}, title={Entwicklung einer mobilen Anwendung für Echtzeit-Visualisierung und Archivierung von mehrkanaliger Biosignalaufnahme mit Bluetooth}, supervisor={Liu, Hui and Schultz, Tanja and Laue, Tim}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/BA_Urban_2019.pdf}, author={Urban, Timo} } @bachelorsthesis{Gülpinar2023biosignalVR, school={Universität Bremen}, year={2023}, title={Development of a {Virtual Reality} Application for the Real-Time Visualization and Archiving of Biosignals}, supervisor={Liu, Hui and Schultz, Tanja and Frese, Udo}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/BA_Guelpinar_VR_2023.pdf}, author={Gülpinar, Ciwan} } @bachelorsthesis{Ott2024ASKE, school={Universität Bremen}, year={2024}, title={Plattformübergreifende Software-Implementierung für individuelle Tonart-Anpassung mit Validierung der Brauchbarkeit}, supervisor={Liu, Hui and Schultz, Tanja and Laue, Tim}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/BA_Ott_ASKE_2024.pdf}, author={Ott, Daniel} } @mastersthesis{Lorenzen2024finger_EMG, school={Universität Bremen}, year={2024}, title={Erkennung von Finger-Aktivitäten beim Klavierspiel mit EMG}, supervisor={Liu, Hui and Schultz, Tanja and Shi, Hui}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/MA_Lorenzen_Finger_2024.pdf}, author={Lorenzen, Thorben} } @bachelorsthesis{Zhang2024ECG, school={Universität Bremen}, year={2024}, title={Real-Time Artifact Recognition during ECG Acquisition}, supervisor={Liu, Hui and Schultz, Tanja and Porzel, Robert}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/BA_Zhang_ECG_2024.pdf}, author={Zhang, Shiyao} } @mastersthesis{Wehrmann2024sportsmusic, school={Universität Bremen}, year={2024}, title={Adaption von Musik an die Bewegungsdaten beim Laufen – Implementation und Validierung von ML-Algorithmen für Android-Applikationen}, supervisor={Liu, Hui and Schultz, Tanja and Clemens, Joachim}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/MA_Wehrmann_Sportsmusic_2024.pdf}, author={Wehrmann, Hannes} } @comment{Old page: http://csl.anthropomatik.kit.edu/theses_2759.php} @phdthesis{wand2014advancing, school={Karlsruher Institut für Technologie}, title={Advancing Electromyographic Continuous Speech Recognition: Signal Preprocessing and Modeling}, year={2014}, supervisor={Schultz, Tanja and Green, Philip}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Diss_Wand_Michael.pdf}, author={Wand, Michael} } @comment{Old page: http://csl.anthropomatik.kit.edu/theses_1994.php} @phdthesis{hsiao2012generalized, school={Carnegie Mellon University}, title={Generalized Discriminative Training for Speech Recognition}, year={2012}, supervisor={Schultz, Tanja and Black, Alan and Metze, Florian and Saon, George}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/PhD-Hsiao.pdf}, author={Hsiao, Roger} } @comment{Old page: http://csl.anthropomatik.kit.edu/theses_1989.php} @phdthesis{prahallad2010automatic, school={Carnegie Mellon University}, title={Automatic Building of Synthetic Voices from Audio Books}, year={2010}, supervisor={Black, Alan W and Ravishankar, Mosur and Schultz, Tanja and Tokuda, Keiichi}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/PhD-Prahallad.pdf}, author={Prahallad, Kishore} } @comment{Old page: http://csl.anthropomatik.kit.edu/theses_1999.php} @phdthesis{tam2009rapid, school={Carnegie Mellon University}, year={2009}, title={Rapid Unsupervised Topic Adaptation - a Latent Semantic Approach}, supervisor={Schultz, Tanja and Waibel, Alex and Vogel, Stephan and Khudanpur, Sanjeev P.}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/PhD-Tam.pdf}, author={Tam, Yik-Cheung} } @comment{Old page: http://csl.anthropomatik.kit.edu/theses_1261.php} @phdthesis{jou2008automatic, school={Carnegie Mellon University}, title={Automatic Speech Recognition on Vibrocervigraphic and Electromyographic Signals}, year={2008}, supervisor={Schultz, Tanja and Waibel, Alex}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/PhD-Jou.pdf}, author={Jou, Szu-Chen (Stan)} } @comment{Old page: http://csl.anthropomatik.kit.edu/theses_1262.php} @phdthesis{laskowski2006vocal, school={Carnegie Mellon University}, year={2006}, title={Vocal Interaction in Multiparty Conversation}, author={Laskowski, Kornel} } @comment{Old page: http://csl.anthropomatik.kit.edu/theses_1263.php} @phdthesis{tomokiyo2001recognizing, school={Carnegie Mellon University}, year={2001}, title={Recognizing non-native speech: Characterizing and adapting to non-native usage in speech recognition}, author={Tomokiyo-Mayfield, Laura}, supervisor={Waibel, Alex and Bernstein, Jared and Eskenazi, Maxine and Schulz, Tanja and Ward, Wayne} } @comment{Old page: http://csl.anthropomatik.kit.edu/theses_1264.php} @phdthesis{schultz2000multilinguale, school={Universit\"at Karlsruhe}, title={Multilinguale Spracherkennung - Kombination akustischer Modelle zur Portierung auf neue Sprachen}, year={2000}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_Diss.pdf}, author={Schultz, Tanja} } @inproceedings{weiner2016towards, title={{Towards Automatic Transcription of ILSE -- an Interdisciplinary Longitudinal Study of Adult Development and Aging}}, author={Jochen Weiner and Claudia Frankenberg and Dominic Telaar and Britta Wendelstein and Johannes Schr\"oder and Tanja Schultz}, booktitle={Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)}, year={2016}, abstract={The Interdisciplinary Longitudinal Study on Adult Development and Aging (ILSE) was created to facilitate the study of challenges posed by rapidly aging societies in developed countries such as Germany. ILSE contains over 8,000 hours of biographic interviews recorded from more than 1,000 participants over the course of 20 years. Investigations on various aspects of aging, such as cognitive decline, often rely on the analysis of linguistic features which can be derived from spoken content like these interviews. However, transcribing speech is a time and cost consuming manual process and so far only 380 hours of ILSE interviews have been transcribed. Thus, it is the aim of our work to establish technical systems to fully automatically transcribe the ILSE interview data. The joint occurrence of poor recording quality, long audio segments, erroneous transcriptions, varying speaking styles & crosstalk, and emotional & dialectal speech in these interviews presents challenges for automatic speech recognition (ASR). We describe our ongoing work towards the fully automatic transcription of all ILSE interviews and the steps we implemented in preparing the transcriptions to meet the interviews' challenges. Using a recursive long audio alignment procedure 96 hours of the transcribed data have been made accessible for ASR training.}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/LREC2016_WeinerEtAl.pdf}, poster={http://www.csl.uni-bremen.de/cms/images/documents/publications/LREC2016_WeinerEtAl_poster.pdf} } @inproceedings{weiner2016speechbased, title={{Speech-Based Detection of Alzheimer's Disease in Conversational German}}, author={Jochen Weiner and Christian Herff and Tanja Schultz}, booktitle={{INTERSPEECH} 2016 -- 17th Annual Conference of the International Speech Communication Association}, year={2016}, abstract={The worldwide population is aging. With a larger population of elderly people, the numbers of people affected by cognitive impairment such as Alzheimer’s disease are growing. Unfortunately, there is no known cure for Alzheimer’s disease. The only way to alleviate it’s serious effects is to start therapy very early before the disease has wrought too much irreversible damage. Current diagnostic procedures are neither cost nor time efficient and therefore do not meet the demands for frequent mass screening required to mitigate the consequences of cognitive impairments on the global scale. We present an experiment to detect Alzheimer’s disease using spontaneous conversational speech. The speech data was recorded during biographic interviews in the Interdisciplinary Longitudinal Study on Adult Development and Aging (ILSE), a large data resource on healthy and satisfying aging in middle adulthood and later life in Germany. From these recordings we extract ten speech-based features using voice activity detection and transcriptions. In an experimental setup with 98 data samples we train a linear discriminant analysis classifier to distinguish subjects with Alzheimer’s disease from the control group. This setup results in an F-score of 0.8 for the detection of Alzheimer’s disease, clearly showing our approach detects dementia well.}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Interspeech2016_WeinerEtAl.pdf}, poster={http://www.csl.uni-bremen.de/cms/images/documents/publications/Interspeech2016_WeinerEtAl_poster.pdf}, doi={10.21437/Interspeech.2016-100} } @inproceedings{weiner2016detection, title={{Detection of Intra-Personal Development of Cognitive Impairment From Conversational Speech}}, author={Jochen Weiner and Tanja Schultz}, booktitle={12th ITG Conference on Speech Communication}, year={2016}, abstract={As the population in developed countries is aging, cognitive impairment such as Alzheimer’s disease becomes an urging challenge for these societies. In order to mitigate the consequences, diagnosing cognitive impairment early is crucial. We present automatic detection of an intra-personal development of cognitive impairment from speech. Using conversational speech data from the ILSE corpus we detect subjects which were considered cognitively healthy at one examination and were diagnosed with a cognitive impairment at a later examination. From the speech recordings we extract 14 speech-based features using voice activity detection and transcriptions. With these features we train a linear discriminant analysis classifier that distinguishes subjects who developed a cognitive impairment from subjects who did not. The classifier achieves an accuracy of 80.4\%, classifying half the cognitively impaired subjects correctly and assigning that label to hardly any cognitively health subjects. This shows our approach is well suited for longitudinal cognitive status monitoring.}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ITGSpeech2016_WeinerEtAl.pdf} } @phdthesis{schlippe2014rapid, school={Karlsruher Institut für Technologie}, title={{Rapid Generation of Pronunciation Dictionaries for New Domains and Languages}}, year={2014}, supervisor={Schultz, Tanja and Davel, Marelie}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/PhD-Schlippe.pdf}, author={Schlippe, Tim} } @phdthesis{vu2014automatic, school={Karlsruher Institut für Technologie}, title={{Automatic Speech Recognition for Low-resource Languages and Accents Using Multilingual and Crosslingual Information}}, year={2014}, supervisor={Schultz, Tanja and Barnard, Etienne}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/PhD-Vu.pdf}, author={Vu, Thang} } @phdthesis{telaar2015error, school={Karlsruher Institut für Technologie}, title={{Error Correction based on Error Signatures applied to automatic speech recognition}}, year={2015}, supervisor={Schultz, Tanja and Tichy, Walter F.}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/PhD-Telaar.pdf}, author={Telaar, Dominic} } @phdthesis{putze2014adaptive, school={Karlsruher Institut für Technologie}, title={{Adaptive Cognitive Interaction Systems}}, year={2014}, supervisor={Schultz, Tanja and Funke, Joachim}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/PhD-Putze.pdf}, author={Putze, Felix} } @phdthesis{heger2015advancing, school={Karlsruher Institut für Technologie}, title={{Advancing Pattern Recognition Techniques for Brain-Computer Interfaces: Optimizing Discriminability, Compactness, and Robustness}}, year={2015}, supervisor={Schultz, Tanja and Stiefelhagen, Reiner}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/PhD-Heger.pdf}, author={Heger, Dominic} } @phdthesis{amma2015modellierung, school={Karlsruher Institut für Technologie}, title={{Modellierung und Erkennung dreidimensionaler Handschrift mittels Inertialsensorik}}, year={2015}, supervisor={Schultz, Tanja and Asfour, Tamim}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/PhD-Amma.pdf}, author={Amma, Christoph} } @phdthesis{gehrig2015automatic, school={Karlsruher Institut für Technologie}, title={{Automatic Recognition of Concurrent and Coupled Human Motion Sequences}}, year={2015}, supervisor={Schultz, Tanja and Dillmann, Rüdiger}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/PhD-Gehrig.pdf}, author={Gehrig, Dirk} } @inproceedings{telaar2016error, title={{Error Signatures to identify Errors in ASR in an unsupervised fashion}}, author={Dominic Telaar and Jochen Weiner and Tanja Schultz}, year={2015}, booktitle={Proceedings of the Errare Workshop (ERRARE 2015)}, abstract={Large scale ASR systems are trained on thousands of hours of speech. Usually, many of these training data were automatically transcribed by another ASR system due to a lack of manual transcriptions and a lack of resources to transcribe them. Systems trained in such a fashion are biased towards the transcription system. In the past, confidence models have been investigated to exclude data from training. We propose to investigate areas of low confidence by extending our previous work. For this purpose we aggregate potential errors of ASR systems by ascribing a list of attributes to each potential error and find a set of attributes which best describe the errors encountered on an automatically transcribed set. We call these characteristic sets of attributes Error Signatures. Examples of attributes are word identity, phonemes, acoustic models, word context, speaker id, and language id. For each Error Signatures, an error ratio is computed, giving the probability that the signature properly describes the error. Error ratios and occurrence frequencies are used to sort the signatures and present them to an expert to fix the Error Signatures underlying shortcomings of the ASR system.}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/TelaarEtAl_Errare2015.pdf} } @mastersthesis{palyafari2015, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/palyafari2015.pdf}, school={Karlsruher Institut für Technologie}, title={{Continuous Activity Recognition for an Intelligent Knee Orthosis; An Out-of-Lab Study}}, year={2015}, supervisor={Amma, Christoph and Georgi, Marcus and Schultz, Tanja}, author={Palyaf\'{a}ri, Ren\'{a}ta}, } @bachelorsthesis{dittrich2015speaker, school={Karlsruher Institut für Technologie}, title={{Speaker Diarization for ILSE-Interviews}}, year={2015}, supervisor={Weiner, Jochen and Schultz, Tanja}, author={Dittrich, Florian}, } @studentresearchproject{strentzsch2015deanonymization, school={Karlsruher Institut für Technologie}, title={{Deanonymization of anonymized transcripts}}, year={2015}, supervisor={Weiner, Jochen and Schultz, Tanja}, author={Strentzsch, Gunnar}, } @bachelorsthesis{grimm2015modellierung, school={Karlsruher Institut für Technologie}, title={{Modellierung von Satzenden für automatische Spracherkennung}}, year={2015}, supervisor={Weiner, Jochen and Schultz, Tanja}, author={Grimm, Daniela}, } @mastersthesis{costa2015noise, school={Karlsruher Institut für Technologie / Universitat Polit\`{e}cnica de Catalunya}, title={{Noise Reduction for ILSE Interviews}}, year={2015}, supervisor={Weiner, Jochen and Schultz, Tanja and Moreno Bilbao, Asunci\'{o}n}, author={Pastrana Costa, Asunci\'{o}n}, } @inproceedings{putze_starring_2016, address = {Gothenborg, Sweden}, title = {Starring into the void? {Classifying} {Internal} vs. {External} {Attention} from {EEG}}, booktitle = {Proceedings of 9th {Nordic} {Conference} on {Human}-{Computer} {Interaction} ({NordiCHI})}, author = {Putze, Felix and Scherer, Maximilian and Schultz, Tanja}, year = {2016} } @inproceedings{putze_model-driven_2016, address = {Bremen, Germany}, title = {Model-driven interaction strategies of a dialog system for navigation and information}, booktitle = {Proceedings of 13th {Biannual} {Conference} of the {German} {Cognitive} {Science} {Society}}, author = {Putze, Felix and Bordolo, Elias and Schultz, Tanja}, year = {2016} } @inproceedings{schultz_i-care:_2016, address = {Bremen, Germany}, title = {I-{CARE}: {Individual} activation of people with dementia}, booktitle = {Proceedings of 13th {Biannual} {Conference} of the {German} {Cognitive} {Science} {Society}}, author = {Schultz, Tanja and Putze, Felix and Schulze, Timo and Mikut, Ralf and Doneit, Wolfgang and Kruse, Andreas and Depner, Anamaria and Franz, Ingo and Engels, Marc Aurel and Gaerte, Philipp and Bothe, Dietmar and Ziegler, Christof and Maucher, Irene and Ricken, Michael and Dimitrov, Todor and Herzig, Joachim and Bernardin, Keni and Gehrig, Tobias and Lohse, Jana and Adam, Marion and Fischer, Monika and Volpe, Massimo and Simon, Clarissa}, year = {2016}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/icarekogwis16schultz.pdf} } @article{ehret_technikbasiertes_2016, title = {Technikbasiertes {Spiel} von {Tagespflegebesuchern} mit und ohne {Demenz}}, issn = {0948-6704, 1435-1269}, language = {de}, urldate = {2016-09-29}, journal = {Zeitschrift für Gerontologie und Geriatrie}, author = {Ehret, S. and Putze, F. and Miller-Teynor, H. and Kruse, A. and Schultz, T.}, month = jul, year = {2016}, pages = {1--10}, } @inproceedings{putze_intervention-free_2016, address = {Tokyo, Japan}, title = {Intervention-{Free} {Selection} using {EEG} and {Eye} {Tracking}}, booktitle = {Proceedings of 18th {ACM} {International} {Conference} on {Multimodal} {Interaction}}, author = {Putze, Felix and Hild, Jutta and Popp, Johannes and Beyerer, Jürgen and Schultz, Tanja}, year = {2016} } @incollection{stiefelhagen_aktiv_2016, address = {Stuttgart, Germany}, title = {{AKTIV} mit {Demenz} - technischen {Aktivierungssystemen} sei {Dank}}, booktitle = {100! {Was} die {Wissenschaft} vom {Altern} weiß}, publisher = {Hirzel, S., Verlag}, author = {Stiefelhagen, Rainer and Schultz, Tanja and Putze, Felix and Kruse, Andreas and Metz, Brigitte}, year = {2016}, pages = {127--136} } @inproceedings{weiner2017manual, title={{Manual and Automatic Transcription in Dementia Detection from Speech}}, author={Jochen Weiner and Mathis Engelbart and Tanja Schultz}, booktitle={{INTERSPEECH} 2017 -- 18\textsuperscript{th} Annual Conference of the International Speech Communication Association}, year={2017}, abstract={As the population in developed countries is aging, larger numbers of people are at risk of developing dementia. In the near future there will be a need for time- and cost-efficient screening methods. Speech can be recorded and analyzed in this manner, and as speech and language are affected early on in the course of dementia, automatic speech processing can provide valuable support for such screening methods. We present two pipelines of feature extraction for dementia detection: the manual pipeline uses manual transcriptions while the fully automatic pipeline uses transcriptions created by automatic speech recognition (ASR). The acoustic and linguistic features that we extract need no language specific tools other than the ASR system. Using these two different feature extraction pipelines we automatically detect dementia. Our results show that the ASR system’s transcription quality is a good single feature and that the features extracted from automatic transcriptions perform similar or slightly better than the features extracted from the manual transcriptions.}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Interspeech2017_WeinerEtAl.pdf}, poster={http://www.csl.uni-bremen.de/cms/images/documents/publications/Interspeech2017_WeinerEtAl_poster.pdf}, } @inproceedings{weiner2017bbdc, author = {Weiner, Jochen and Diener, Lorenz and Stelter, Simon and Externest, Eike and K{\"u}hl, Sebastian and Herff, Christian and Putze, Felix and Schulze, Timo and Salous, Mazen and Liu, Hui and K{\"u}ster, Dennis and Schultz, Tanja}, title = {Bremen Big Data Challenge 2017: {Predicting} University Cafeteria Load}, booktitle = {{KI} 2017: Advances in Artificial Intelligence}, editor = {Kern-Isberner, Gabriele and F{\"u}rnkranz, Johannes and Thimm, Matthias}, year = {2017}, publisher = {Springer International Publishing}, address = {Cham}, pages = {380--386}, isbn = {978-3-319-67190-1}, doi = {10.1007/978-3-319-67190-1_35}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/WeinerEtAl_KI2017.pdf}, abstract = {Big data is a hot topic in research and industry. The availability of data has never been as high as it is now. Making good use of the data is a challenging research topic in all aspects of industry and society. The Bremen Big Data Challenge invites students to dig deep into big data. In this yearly event students are challenged to use the month of March to analyze a big dataset and use the knowledge they gained to answer a question. In this year's Bremen Big Data Challenge students were challenged to predict the load of the university cafeteria from the load of past years. The best of 24 teams predicted the load with a root mean squared error of 8.6 receipts issued in five minutes, with a fusion system based on the top 5 entries achieving an even better result of 8.28.} } @article{janke2017emg, title={EMG-to-Speech: Direct Generation of Speech From Facial Electromyographic Signals}, volume={25}, number={12}, pages={2375--2385}, year={2017}, month={nov}, day={23}, doi={10.1109/TASLP.2017.2738568}, journal={IEEE/ACM Transactions on Audio, Speech and Language Processing}, author={Janke, Matthias and Diener, Lorenz}, abstract={Silent speech interfaces are systems that enable speech communication even when an acoustic signal is unavailable. Over the last years, public interest in such interfaces has intensified. They provide solutions for some of the challenges faced by today's speech-driven technologies, such as robustness to noise and usability for people with speech impediments. In this paper, we provide an overview over our silent speech interface. It is based on facial surface electromyography (EMG), which we use to record the electrical signals that control muscle contraction during speech production. These signals are then converted directly to an audible speech waveform, retaining important paralinguistic speech cues for information such as speaker identity and mood. This paper gives an overview over our state-of-the-art direct EMG-to-speech transformation system. This paper describes the characteristics of the speech EMG signal, introduces techniques for extracting relevant features, presents different EMG-to-speech mapping methods, and finally, presents an evaluation of the different methods for real-time capability and conversion quality.}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/TASLP-2017-direct-generation.pdf}, } @article{schultz2017biosignal, title={Biosignal-based Spoken Communication: A Survey}, volume={25}, number={12}, pages={2257--2271}, year={2017}, month={nov}, day={23}, doi={10.1109/TASLP.2017.2752365}, journal={IEEE/ACM Transactions on Audio, Speech and Language Processing}, author={Schultz, Tanja and Wand, Michael and Hueber, Thomas and Krusienski Dean J. and Herff, Christian and Brumberg, Jonathan S.}, abstract={Speech is a complex process involving a wide range of biosignals, including but not limited to acoustics. These biosignals—stemming from the articulators, the articulator muscle activities, the neural pathways, and the brain itself — can be used to circumvent limitations of conventional speech processing in particular, and to gain insights into the process of speech production in general. Research on biosignal-based speech processing is a wide and very active field at the intersection of various disciplines, ranging from engineering, computer science, electronics and machine learning to medicine, neuroscience, physiology, and psychology. Consequently, a variety of methods and approaches have been used to investigate the common goal of creating biosignal-based speech processing devices for communication applications in everyday situations and for speech rehabilitation, as well as gaining a deeper understanding of spoken communication. This paper gives an overview of the various modalities, research approaches, and objectives for biosignal-based spoken communication.}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/TASLP-2017-biosignal-based-spoken.pdf}, } @inproceedings{putze_salous_2018iui, author={Putze, Felix and Salous, Mazen and Schultz, Tanja}, title={Detecting Memory-Based Interaction Obstacles with a Recurrent Neural Model of User Behavior}, booktitle={Proceedings of the 2018 International Conference on Intelligent User Interfaces}, series = {IUI '18}, year = {2018}, isbn = {978-1-4503-4945-1/18/03}, location = {National Center of Sciences Building, Tokyo, Japan}, pages = {205--209}, numpages = {5}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/putze_salous_2018iui.pdf}, doi = {10.1145/3172944.3173006}, publisher = {ACM}, address = {Tokyo, Japan}, keywords = {Classification of user behavior, memory, interaction obstacles, LSTMs}, abstract={A memory-based interaction obstacle is a condition which impedes human memory during Human-Computer Interaction, for example a memory-loading secondary task. In this paper, we present an approach to detect the presence of such memory-based interaction obstacles from logged user behavior during system use. For this purpose, we use a recurrent neural network which models the resulting temporal sequences. To acquire a sufficient number of training episodes, we employ a cognitive user simulation. We evaluate the approach with data from a user test and on which we outperform a non-sequential baseline by up to 42% relative.} } @diplomathesis{janke2016emg, school={Karlsruher Institut für Technologie}, title={EMG-to-Speech: Direct Generation of Speech from Facial Electromyographic Signals}, year={2016}, supervisor={Schultz, Tanja}, author={Janke, Matthias}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/janke_thesis.pdf}, } @inproceedings{salous_putze_2018esann, author={Salous, Mazen and Putze, Felix}, title={Behaviour-Based Working Memory Capacity Classification Using Recurrent Neural Networks}, booktitle={{ESANN} 2018 -- 26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning}, isbn = {978-2-87587-047-6}, pages = {159--164}, numpages = {6}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/salous_putze_2018esann.pdf}, address = {Brugge, Belgium}, year={2018}, abstract={A user's working memory capacity is a crucial factor for successful Human Computer Interaction (HCI). While reliable tests for working memory capacity are available, they are time-consuming, stressful, and not well-integrated into HCI applications. This paper presents a classifier based on Long Short Term Memory networks to exploit sparse temporal dependencies in behavioural data, collected in a complex, memory-intense interaction task, to classify working memory capacity. A cognitive user simulation is introduced to generate additional training data episodes that follow the behaviour of existing real data. We show that the classifier outperforms a linear baseline especially for short segments of data.}, } @inproceedings{angrick_2018esann, author={Angrick, Miguel and Herff, Christian and Johnson, Garett and Shih, Jerry and Krusienski, Dean and Schultz, Tanja}, title={{Interpretation of Convolutional Neural Networks for Speech Regression from Electrocorticography}}, booktitle={{ESANN} 2018 -- 26th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning}, isbn = {978-2-87587-047-6}, pages = {7--12}, numpages = {6}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/angrick_2018esann.pdf}, address = {Brugge, Belgium}, year={2018}, abstract={The direct synthesis of continuously spoken speech from neural activity is envisioned to enable fast and intuitive Brain-Computer Interfaces. Earlier results indicate that intracranial recordings reveal very suitable signal characteristics for direct synthesis. To map the complex dynamics of neural activity to spectral representations of speech, Convolutional Neural Networks (CNNs) can be trained. However, the resulting networks are hard to interpret and thus provide little opportunity to gain insights on neural processes underlying speech. Here, we show that CNNs are useful to reconstruct speech from intracranial recordings of brain activity and propose an approach to interpret the trained CNNs.}, } @inproceedings{weiner2018investigating, title={{Investigating the Effect of Audio Duration on Dementia Detection using Acoustic Features}}, author={Jochen Weiner and Miguel Angrick and Srinivasan Umesh and Tanja Schultz}, booktitle={{INTERSPEECH} 2018 -- 19th Annual Conference of the International Speech Communication Association}, year={2018}, abstract={This paper presents recent progress toward our goal to enable area-wide pre-screening methods for the early detection of dementia based on automatically processing conversational speech of a representative group of more than 200 subjects. We focus on conversational speech since it is the natural form of communication that can be recorded unobtrusively, without adding stress to subjects, and without the need of controlled clinical settings. We describe our unsupervised process chain consisting of voice activity detection and speaker diarization followed by extraction of features and detection of early signs of dementia. The unsupervised system achieves up to 0.645 unweighted average recall (UAR) and compares favorably to a system that was carefully designed on manually annotated data. To further lower the burden for subjects, we investigate UAR over speech duration, and find that about 12 minutes of interview are sufficient to achieve the best UAR.}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Interspeech2018_WeinerEtAl.pdf}, } @inproceedings{weiner2018selecting, title={{Selecting Features for Automatic Screening for Dementia based on Speech}}, author={Jochen Weiner and Tanja Schultz}, booktitle={Speech and Computer}, year={2018}, publisher="Springer International Publishing", pages="747--756", doi={10.1007/978-3-319-99579-3_76}, abstract={As the population in developed countries ages, larger numbers of people are at risk of developing dementia. In the near future large-scale time- and cost-efficient screening methods will be needed. Speech can be recorded and analyzed in this manner, and as speech and language are affected early on in the course of dementia, automatic speech processing can provide valuable support for such screening methods. We have developed acoustic and linguistic features for dementia screening and established that a combination of acoustic and linguistic features provides the best results. However, our full set of 429 fine-grained features from 15 feature types is too large to train a robust model on limited training data. We therefore need to select features to use for dementia screening. We employ forward feature selection nested in a cross-validation and identify the most commonly selected features. Both acoustic and linguistic features from seven different feature types are selected. Using sets of these features we obtain a 0.819 unweighted average recall which is a strong improvement over previous results.}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Specom2018_WeinerEtAl.pdf}, } @inproceedings{weiner2018automatic, title={{Automatic Screening for Transition into Dementia using Speech}}, author={Jochen Weiner and Tanja Schultz}, booktitle={13th ITG Conference on Speech Communication}, year={2018}, abstract={Diagnosing dementia early is crucial in mitigating the consequences of the disease for patients, their care-givers and relatives. We present automatic screening for personal transition into dementia from speech using information from more than one point in time. Using conversational speech data from the ILSE corpus we screen subjects if they transition from a cognitively healthy state to a state of dementia. We use both acoustic and linguistic features from two pipelines of feature extraction: the manual pipeline uses manual transcriptions while the fully automatic pipeline uses transcriptions created by automatic speech recognition (ASR). Using these two different feature extraction pipelines we automatically screen for dementia transition, where the fully automatic pipeline performs the whole screening process fully automatically. Our results show the features extracted from automatic transcriptions outperform the features extracted from the manual transcriptions.}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ITG2018_WeinerEtAl.pdf} } @inproceedings{diener2018investigating, title={{Investigating Objective Intelligibility in Real-Time EMG-to-Speech Conversion}}, author={Lorenz Diener and Tanja Schultz}, booktitle={{INTERSPEECH} 2018 -- 19th Annual Conference of the International Speech Communication Association}, year={2018}, abstract={This paper presents an analysis of the influence of various system parameters on the output quality of our neural network based real-time EMG-to-Speech conversion system. This EMG-to-Speech system allows for the direct conversion of facial surface electromyographic signals into audible speech in real time, allowing for a closed-loop setup where users get direct audio feedback. Such a setup opens new avenues for research and applications through co-adaptation approaches. In this paper, we evaluate the influence of several parameters on the output quality, such as time context, EMG-Audio delay, network-, training data- and Mel spectrogram size. The resulting output quality is evaluated based on the objective output quality measure STOI.}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/IS2018_EMG_Realtime.pdf}, } @inproceedings{diener2018session, title={{Session-Independent Array-Based EMG-to-Speech Conversion using Convolutional Neural Networks}}, author={Lorenz Diener and Gerrit Felsch and Miguel Angrick and Tanja Schultz}, booktitle={13th ITG Conference on Speech Communication}, year={2018}, abstract={This paper presents an evaluation of the performance of EMG-to-Speech conversion based on convolutional neural networks. We present an analysis of two different architectures and network design considerations and evaluate CNN-based systems for their within-session and cross-session performance. We find that they are able to perform on par with feedforward neural networks when trained and evaluated on a single session and outperform them in cross session evaluations.}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ITG2018_EMG_ConvNets.pdf} } @inproceedings{diener2018comparison, title={{A comparison of EMG-to-Speech Conversion for Isolated and Continuous Speech}}, author={Lorenz Diener and Sebastian Bredehöft and Tanja Schultz}, booktitle={13th ITG Conference on Speech Communication}, year={2018}, abstract={This paper presents initial results of performing EMG-to-Speech conversion within our new EMG-to-Speech corpus. This new corpus consists of parallel facial array sEMG and read audible speech signals recorded from multiple speakers. It contains different styles of utterances - continuous sentences, isolated words, and isolated consonant-vowel combinations - which allows us to evaluate the performance of EMG-to-Speech conversion when trying to convert these different styles of utterance as well as the effect of training systems on one style to convert another. We find that our system deals with isolated-word/consonant-vowel utterances better than with continuous speech. We also find that it is possible to use a model trained on one style to convert utterances from another - however, performance suffers compared to training within that style, especially when going from isolated to continuous speech.}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ITG2018_EMG_NewCorpus.pdf} } @inproceedings{liu2018har_framework, title = {{ASK}: {A} Framework for Data Acquisition and Activity Recognition}, author = {Liu, Hui and Schultz, Tanja}, booktitle = {Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2018) - Volume 3: BIOSIGNALS}, pages = {262--268}, organization = {INSTICC}, publisher = {SciTePress}, year = {2018}, isbn = {978-989-758-279-0}, issn = {2184-4305}, doi = {10.5220/0006732902620268}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/LiuSchultz_Biosignals2018.pdf}, abstract = {This work puts forward a framework for the acquisition and processing of biosignals to indicate strain on the knee inflicted by human everyday activities. Such a framework involves the appropriate equipment in devices and sensors to capture factors that inflict strain on the knee, the long-term recording and archiving of corresponding multi-sensory biosignal data, the semi-automatic annotation and segmentation of these data, and the person-dependent or person-adaptive automatic recognition of strain. In this paper we present first steps toward our goal, i.e. person-dependent recognition of a small set of human everyday activities. The focus here is on the fully automatic end-to-end processing from signal input to recognition output. The framework was applied to collect and process a small pilot dataset from one person for a proof-of-concept validation and achieved 97\% accuracy in recognizing instances of seven daily activities.} } @inproceedings{liu2019realtime_har, //note = {Best Student Paper}, title = {A Wearable Real-time Human Activity Recognition System using Biosensors Integrated into a Knee Bandage}, author = {Liu, Hui and Schultz, Tanja}, booktitle = {Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2019) - Volume 1: BIODEVICES}, pages = {47--55}, organization = {INSTICC}, publisher = {SciTePress}, year = {2019}, isbn = {978-989-758-353-7}, issn = {2184-4305}, doi = {10.5220/0007398800470055}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/LiuSchultz_Biodevices2019.pdf}, abstract = {This work introduces an innovative wearable real-time Human Activity Recognition (HAR) system. The system processes and decodes various biosignals that are captured from biosensors integrated into a knee bandage. The presented work includes (1) the selection of an appropriate equipment in terms of devices and sensors to capture human activity-related biosignals in real time, (2) the experimental tuning of system parameters which balances recognition accuracy with real-time performance, (3) the intuitive visualization of biosignals as well as n-best recognition results in the graphical user interfaces, and (4) the on-the-air extensions for rapid prototyping of applications. The presented system recognizes seven daily activities: sit, stand, stand up, sit down, walk, turn left and turn right. The amount of activity classes to be recognized can be easily extended by the "plug-and-play" function. To the best of our knowledge, this is the first work which demonstrates a real-time HAR system using biosensors integrated into a knee bandage.} } @inproceedings{salous_putze_2018icmi_mcpmd, author={Salous, Mazen and Putze, Felix and Schultz, Tanja and Hild Jutta and Beyerer, J\"{u}rgen}, title={Investigating Static and Sequential Models for Intervention-Free Selection Using Multimodal Data of EEG and Eye Tracking}, booktitle={{ICMI} 2018 -- ICMI 2018 Workshop on Modeling Cognitive Processes from Multimodal Data}, isbn = {978-1-4503-5692-3}, numpages = {6}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/salous_putze_2018icmi_mcpmd.pdf}, address = {Boulder, Colorado, USA}, year={2018}, abstract={Multimodal data is increasingly used in cognitive prediction models to better analyze and predict different user cognitive processes. Classifiers based on such data, however, have different performance characteristics. We discuss in this paper an intervention-free selection task using multimodal data of EEG and eye tracking in three different models. We show that a sequential model, LSTM, is more sensitive but less precise than a static model SVM. Moreover, we introduce a confidence-based Competition-Fusion model using both SVM and LSTM. The fusion model further improves the recall compared to either SVM or LSTM alone, without decreasing precision compared to LSTM. According to the results, we recommend SVM for interactive applications which require minimal false positives (high precision), and recommend LSTM and highly recommend Competition-Fusion Model for applications which handle intervention-free selection requests in an additional post-processing step, requiring higher recall than precision.}, } @article{garcia_dynamics_2016, title = {The dynamics of emotions in online interaction}, volume = {3}, issn = {2054-5703}, doi = {10.1098/rsos.160059}, pages = {160059}, number = {8}, journal = {Royal Society Open Science}, author = {Garcia, David and Kappas, Arvid and Küster, Dennis and Schweitzer, Frank}, urldate = {2018-08-17}, year = {2016}, langid = {english}, abstract = {We study the changes in emotional states induced by reading and participating in online discussions, empirically testing a computational model of online emotional interaction. Using principles of dynamical systems, we quantify changes in valence and arousal through subjective reports, as recorded in three independent studies including 207 participants (110 female). In the context of online discussions, the dynamics of valence and arousal are composed of two forces: an internal relaxation towards baseline values independent of the emotional charge of the discussion, and a driving force of emotional states that depends on the content of the discussion. The dynamics of valence show the existence of positive and negative tendencies, while arousal increases when reading emotional content regardless of its polarity. The tendency of participants to take part in the discussion increases with positive arousal. When participating in an online discussion, the content of participants' expression depends on their valence, and their arousal significantly decreases afterwards as a regulation mechanism. We illustrate how these results allow the design of agent-based models to reproduce and analyze emotions in online communities. Our work empirically validates the microdynamics of a model of online collective emotions, bridging online data analysis with research in the laboratory.}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/Garcia et al. - 2016 - The dynamics of emotions in online interaction.pdf:C\:\\Users\\Dennis Küster\\Zotero\\storage\\L5EQHBNB\\Garcia et al. - 2016 - The dynamics of emotions in online interaction.pdf:application/pdf} } @article{swiderska_avatars_2018, title = {Avatars in Pain: Visible Harm Enhances Mind Perception in Humans and Robots}, issn = {0301-0066, 1468-4233}, doi = {10.1177/0301006618809919}, shorttitle = {Avatars in Pain}, abstract = {Previous research has shown that when people read vignettes about the infliction of harm upon an entity appearing to have no more than a liminal mind, their attributions of mind to that entity increased. Currently, we investigated if the presence of a facial wound enhanced the perception of mental capacities (experience and agency) in response to images of robotic and human-like avatars, compared with unharmed avatars. The results revealed that harmed versions of both robotic and human-like avatars were imbued with mind to a higher degree, irrespective of the baseline level of mind attributed to their unharmed counterparts. Perceptions of capacity for pain mediated attributions of experience, while both pain and empathy mediated attributions of abilities linked to agency. The findings suggest that harm, even when it appears to have been inflicted unintentionally, may augment mind perception for robotic as well as for nearly human entities, at least as long as it is perceived to elicit pain.}, pages = {030100661880991}, journal = {Perception}, author = {Swiderska, Aleksandra and Küster, Dennis}, urldate = {2018-12-03}, year = {2018}, langid = {english}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/Swiderska and Küster - 2018 - Avatars in Pain Visible Harm Enhances Mind Percep.pdf} } @article{kuster_social_2018, title = {Social Effects of Tears and Small Pupils Are Mediated by Felt Sadness: An Evolutionary View}, volume = {16}, issn = {1474-7049, 1474-7049}, doi = {10.1177/1474704918761104}, shorttitle = {Social Effects of Tears and Small Pupils Are Mediated by Felt Sadness}, abstract = {Small pupils elicit empathic socioemotional responses comparable to those found for emotional tears. This might be understood in an evolutionary context. Intense emotional tearing increases tear film volume and disturbs tear layer uniformity, resulting in blurry vision. A constriction of the pupils may help to mitigate this handicap, which in turn may have resulted in a perceptual association of both signals. However, direct empirical evidence for a role of pupil size in tearful emotional crying is still lacking. The present study examined socioemotional responses to different pupil sizes, combined with the presence (absence) of digitally added tears superimposed upon expressively neutral faces. Data from 50 subjects showed significant effects of observing digitally added tears in avatars, replicating previous findings for increased perceived sadness elicited by tearful photographs. No significant interactions were found between tears and pupil size. However, small pupils likewise elicited a significantly greater wish to help in observers. Further analysis showed a significant serial mediation of the effects of tears on perceived wish to help via perceived and then felt sadness. For pupil size, only felt sadness emerged as a significant mediator of the wish to help. These findings support the notion that pupil constriction in the context of intense sadness may function to counteract blurry vision. Pupil size, like emotional tears, appears to have acquired value as a social signal in this context.}, pages = {147470491876110}, number = {1}, journal = {Evolutionary Psychology}, author = {Küster, Dennis}, urldate = {2019-01-07}, year = {2018}, langid = {english}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/Küster - 2018 - Social Effects of Tears and Small Pupils Are Media.pdf} } @article{obaid_endowing_2018, title = {Endowing a Robotic Tutor with Empathic Qualities: Design and Pilot Evaluation}, pages = {32}, author = {Obaid, Mohammad and Aylett, Ruth and Barendregt, Wolmet and Basedow, Christina and Corrigan, Lee J and Hall, Lynne and Jones, Aidan and Kappas, Arvid and Küster, Dennis and Paiva, Ana and Papadopoulos, Fotis and Serholt, Sofia and Castellano, Ginevra}, year = {2018}, langid = {english}, abstract = {As increasingly more research efforts are geared towards creating robots that can teach and interact with children in educational contexts, it has been speculated that endowing robots with artificial empathy may facilitate learning. In this paper, we provide a background to the concept of empathy, and how it factors into learning. We then present our approach to equipping a robotic tutor with several empathic qualities, describing the technical architecture and its components, a map-reading learning scenario developed for an interactive multitouch table, as well as the pedagogical and empathic strategies devised for the robot. We also describe the results of a pilot study comparing the robotic tutor with these empathic qualities against a version of the tutor without them. The pilot study was performed with 26 school children aged 10-11 at their school. Results revealed that children in the test condition indeed rated the robot as more empathic than children in the control condition. Moreover, we explored several related measures, such as relational status and learning effect, yet no other significant differences were found. We further discuss these results and provide insights into future directions.}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/Obaid et al. - 2018 - Endowing a Robotic Tutor with Empathic Qualities .pdf} } @article{papadopoulos_relative_2016, title = {Do relative positions and proxemics affect the engagement in a human-robot collaborative scenario?}, volume = {17}, issn = {1572-0373, 1572-0381}, doi = {10.1075/is.17.3.01pap}, abstract = {This paper investigates the effects of relative position and proxemics in the engagement process involved in Human-Robot collaboration. We evaluate the differences between two experimental placement conditions (frontal vs. lateral) for an autonomous robot in a collaborative task with a user across two different types of robot behaviours (helpful vs. neutral). The study evaluated placement and behaviour types around a touch table with 85 participants by measuring gaze, smiling behaviour, distance from the task, and finally electrodermal activity. Results suggest an overall user preference and higher engagement rates with the helpful robot in the frontal position. We discuss how behaviours and position of the robot relative to a user may affect user engagement and collaboration, in particular when the robot aims to provide help via socio-emotional bonding.}, pages = {321--347}, number = {3}, journal = {Interaction Studies}, author = {Papadopoulos, Fotios and Küster, Dennis and Corrigan, Lee J. and Kappas, Arvid and Castellano, Ginevra}, urldate = {2019-01-07}, year = {2016}, langid = {english}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/Papadopoulos et al. - 2016 - Do relative positions and proxemics affect the eng.pdf} } @article{kuster_you_2018, title = {You are What You Wear: Unless You Moved—Effects of Attire and Posture on Person Perception}, issn = {0191-5886, 1573-3653}, doi = {10.1007/s10919-018-0286-3}, shorttitle = {You are What You Wear}, abstract = {While first impressions are often based on appearance cues, little is known about how these interact with information from other channels. The present research aimed to investigate the impact of occupational stereotypes, evoked by attire, as well as posture on person per‑ception. For this, computer animation was used to create avatars with different types of attire (nurse, military, casual) and posture (open, closed). In Study 1 (N = 164), participants attributed significantly more empathy to avatars wearing a nurse versus a military uniform or casual outfit. When adding posture as an additional cue, Study 2 (N = 312) showed that ratings of empathy and dominance were affected by both attire and posture. This effect was replicated in Study 3 (N = 163) for female avatars, in the sense that open postures in nurses increased empathy ratings and decreased dominance ratings, which both in turn led to greater perceived competence. By contrast, for male avatars, posture did not affect attri‑butions of competence directly. Rather, attire predicted perceived dominance directly, as well as through perceived empathy. The present findings suggest that both posture, and occupational information evoked by attire, are used to infer personal characteristics. How‑ever, the strength of each cue may vary with the gender of the target.}, journal = {Journal of Nonverbal Behavior}, author = {Küster, Dennis and Krumhuber, Eva G. and Hess, Ursula}, urldate = {2019-01-07}, year = {2018}, langid = {english}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/Küster et al. - 2018 - You are What You Wear Unless You Moved—Effects of.pdf} } @article{krumhuber_review_2017, title = {A {Review} of {Dynamic} {Datasets} for {Facial} {Expression} {Research}}, volume = {9}, issn = {1754-0739, 1754-0747}, url = {http://journals.sagepub.com/doi/10.1177/1754073916670022}, doi = {10.1177/1754073916670022}, abstract = {Temporal dynamics have been increasingly recognized as an important component of facial expressions. With the need for appropriate stimuli in research and application, a range of databases of dynamic facial stimuli has been developed. The present article reviews the existing corpora and describes the key dimensions and properties of the available sets. This includes a discussion of conceptual features in terms of thematic issues in dataset construction as well as practical features which are of applied interest to stimulus usage. To identify the most influential sets, we further examine their citation rates and usage frequencies in existing studies. General limitations and implications for emotion research are noted and future directions for stimulus generation are outlined.}, language = {en}, number = {3}, urldate = {2019-01-08}, journal = {Emotion Review}, author = {Krumhuber, Eva G. and Skora, Lina and Küster, Dennis and Fou, Linyun}, month = jul, year = {2017}, pages = {280--292}, } @article{choloniewski_temporal_2016, title = {Temporal {Taylor}’s scaling of facial electromyography and electrodermal activity in the course of emotional stimulation}, volume = {90}, issn = {09600779}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0960077916301564}, doi = {10.1016/j.chaos.2016.04.023}, abstract = {High frequency psychophysiological data create a challenge for quantitative modeling based on Big Data tools since they reflect the complexity of processes taking place in human body and its responses to external events. Here we present studies of fluctuations in facial electromyography (fEMG) and electrodermal activity (EDA) massive time series and changes of such signals in the course of emotional stimulation. Zygomaticus major (ZYG; “smiling” muscle) activity, corrugator supercilii (COR; “frowning” muscle) activity, and phasic skin conductance (PHSC; sweating) levels of 65 participants were recorded during experiments that involved exposure to emotional stimuli (i.e., IAPS images, reading and writing messages on an artificial online discussion board). Temporal Taylor’s fluctuations scaling were found when signals for various participants and during various types of emotional events were compared. Values of scaling exponents were close to one, suggesting an external origin of system dynamics and/or strong interactions between system’s basic elements (e.g., muscle fibres). Our statistical analysis shows that the scaling exponents enable identification of high valence and arousal levels in ZYG and COR signals.}, language = {en}, urldate = {2019-01-08}, journal = {Chaos, Solitons \& Fractals}, author = {Chołoniewski, Jan and Chmiel, Anna and Sienkiewicz, Julian and Hołyst, Janusz A. and Küster, Dennis and Kappas, Arvid}, month = sep, year = {2016}, pages = {91--100}, } @article{skowron_applying_2014, title = {Applying a {Text}-{Based} {Affective} {Dialogue} {System} in {Psychological} {Research}: {Case} {Studies} on the {Effects} of {System} {Behaviour}, {Interaction} {Context} and {Social} {Exclusion}}, volume = {6}, issn = {1866-9956, 1866-9964}, shorttitle = {Applying a {Text}-{Based} {Affective} {Dialogue} {System} in {Psychological} {Research}}, url = {http://link.springer.com/10.1007/s12559-014-9271-2}, doi = {10.1007/s12559-014-9271-2}, language = {en}, number = {4}, urldate = {2019-01-08}, journal = {Cognitive Computation}, author = {Skowron, Marcin and Rank, Stefan and Świderska, Aleksandra and Küster, Dennis and Kappas, Arvid}, month = dec, year = {2014}, pages = {872--891}, } @article{sofia_students_2016, title = {Students' {Normative} {Perspectives} on {Classroom} {Robots}}, copyright = {©2016 \© The authors and IOS Press. All rights reserved.}, issn = {0922-6389}, url = {http://www.medra.org/servlet/aliasResolver?alias=iospressISBN&isbn=978-1-61499-707-8&spage=240&doi=10.3233/978-1-61499-708-5-240}, doi = {10.3233/978-1-61499-708-5-240}, abstract = {As robots are becoming increasingly common in society and education, it is expected that autonomous and socially adaptive classroom robots may eventually be given responsible roles in primary education. In this paper, we present the results of a questionnaire study carried out with students enrolled in compulsory education in three European countries. The study aimed to explore students’ normative perspectives on classroom robots pertaining to roles and responsibilities, student-robot relationships, and perceptive and emotional capabilities in robots. The results suggest that, although students are generally positive toward the existence of classroom robots, certain aspects are deemed more acceptable than others.}, language = {en}, urldate = {2019-01-08}, journal = {Frontiers in Artificial Intelligence and Applications}, author = {Sofia, Serholt and Wolmet, Barendregt and Dennis, K\üster and Aidan, Jones and Patr\ícia, Alves-Oliveira and Ana, Paiva}, year = {2016}, pages = {240--251}, } @incollection{kuster_measuring_2017, address = {Cham}, title = {Measuring {Emotions} {Online}: {Expression} and {Physiology}}, isbn = {978-3-319-43639-5}, url = {https://doi.org/10.1007/978-3-319-43639-5_5}, abstract = {Cyberemotions refer to emotions in networks that are a complex function of emotional states in individuals. Thus, measuring cyberemotions frequently involves attempts to estimate emotional states in individuals. Yet, this is not easy, as emotions in individuals are characterized by limited cohesion of the components of response, such as expression in the face, voice, and body, central and peripheral physiological changes, changes in action readiness, as well as subjective experience. There is no gold standard that would identify any of these components by a single criterion. In consequence, modern experimental emotion research has focused on multi-modal assessment of emotions. Different components are targeted at identifying the valence of responses, or the intensity. We will describe paradigms that are particularly tailored for research in the context of cyberemotions and illustrate these with concrete examples of data recorded in our laboratory.}, booktitle = {Cyberemotions: {Collective} {Emotions} in {Cyberspace}}, publisher = {Springer International Publishing}, author = {Küster, Dennis and Kappas, Arvid}, editor = {Holyst, Janusz A.}, year = {2017}, doi = {10.1007/978-3-319-43639-5_5}, pages = {71--93} } @inproceedings{schultz_i-care:_2018, address = {Oldenburg, Germany}, title = {I-{CARE}: {Ein} {Mensch}-{Technik} {Interaktionssystem} zur {Individuellen} {Aktivierung} von {Menschen} mit {Demenz}}, booktitle = {Tagungsband der 1. {Clusterkonferenz} {Zukunft} der {Pflege}}, author = {Schultz, Tanja and Putze, Felix and Schulze, Timo and Steinert, Lars and Mikut, Ralf and Doneit, Wolfgang and Kruse, Andreas and Depner, Anamaria and Franz, Ingo and Engels, Marc Aurel and Gaerte, Philipp and Jünger, Sebastian and Linden, Rene and Ziegler, Christof and Ricken, Michael and Dimitrov, Todor and Herzig, Joachim and Maucher, Irene and Bernardin, Keni and Gehrig, Tobias and Lohse, Jana and Glesing, Kristina and Fischer, Monika and Simon, Clarissa}, year = {2018} } @inproceedings{putze_dozing_2018, address = {Boulder, CO, USA}, title = {Dozing off or {Thinking} {Hard}? {Classifying} {Multi}-dimensional {Attentional} {States} in the {Classroom} from {Video}}, booktitle = {Proceedings of 20th {ACM} {International} {Conference} on {Multimodal} {Interfaces}}, publisher = {ACM}, author = {Putze, Felix and Annerer-Walcher, Sonja and Küster, Dennis and Benedek, Mathias}, year = {2018} } @inproceedings{schulz2019role, title={The Role of Physical Props in VR Climbing Environments}, author={Schulz, Peter and Alexandrovsky, Dmitry and Putze, Felix and Malaka, Rainer and Sch{\"o}ning, Johannes}, booktitle={Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems}, pages={183}, year={2019}, organization={ACM} } @incollection{putze2019methods, title={Methods and Tools for Using BCI with Augmented and Virtual Reality}, author={Putze, Felix}, booktitle={Brain Art}, pages={433--446}, year={2019}, publisher={Springer} } @article{frankenberg_weiner_2019, author={Claudia Frankenberg and Jochen Weiner and Tanja Schultz and Maren Knebel and Christina Degen and Hans-W. Wahl and Johannes Schr\"oder}, title={Perplexity - a new predictor of cognitive changes in spoken language?: - results of the Interdisciplinary Longitudinal Study on Adult Development and Aging (ILSE)}, year={2019}, month={06}, day={22}, journal={Linguistics Vanguard}, volume={5}, note={s2}, issn={2199174X}, doi={10.1515/lingvan-2018-0026}, url={https://www.degruyter.com/view/j/lingvan.2019.5.issue-s2/lingvan-2018-0026/lingvan-2018-0026.xml}, abstract={In addition to memory loss, progressive deterioration of speech and language skills is among the main symptoms at the onset of Alzheimer’s disease (AD) as well as in mild cognitive impairment (MCI). Detailed interview analyses demonstrated early symptoms years before the onset of AD/MCI. Automatic speech processing could be a promising approach to identifying underlying mechanisms in larger studies or even support diagnostics. Perplexity as a measure of predictability of text could be a sensitive indicator of cognitive deterioration. Therefore, voice recordings from the Interdisciplinary Longitudinal Study on Adult Development and Aging were analyzed with regard to neuropsychological parameters in participants that develop MCI/AD or remain cognitively healthy. Preliminary results indicate that perplexity predicts severity of cognitive deficits and information processing speed obtained 10–12 years later in participants who developed MCI/AD in contrast to those who stayed healthy. Findings support the heuristic value of research on the diagnostic potential of automatic speech processing.} } @inproceedings{meier_iros_2018, title = {Synchronized Multimodal Recording of a Table Setting Dataset}, author = {Meier, Moritz and Mason, Celeste and Porzel, Robert and Putze, Felix and Schultz, Tanja}, booktitle = {IROS 2018: Workshop on Latest Advances in Big Activity Data Sources for Robotics \& New Challenges}, year = {2018}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/meier_iros_2018.pdf}, address={Madrid, Spain}, abstract={We present here a description of our initial efforts in developing a Biosignal Acquisition Space and Environment (BASE) to collect a large open access dataset of human everyday activities. The final dataset is planned to consist of synchronously recorded biosignals from 100 participants performing everyday activities while describing their task through use of think-aloud protocols. Biosignals encompass six different modalities, with one first person and seven third person cameras, a nine camera motion capture system, one near distance speech microphone and one far distance room microphone, four channel EMG, 16 channel EEG and an eye tracker. The data is collected in the context of the EASE collaborative research center and is intended to benefit the robotics community. This paper provides details regarding the sensors, devices and software used for the data recording as well as insights into the recorded biosignal data streams.} } @inproceedings{mason_iros_2018, title = {Human Activities Data Collection and Labeling using a Think-aloud Protocol in a Table Setting Scenario}, author = {Mason, Celeste and Meier, Moritz and Ahrens, Florian and Fehr, Thorsten and Herrmann, Manfred and Putze, Felix and Schultz, Tanja}, booktitle = {IROS 2018: Workshop on Latest Advances in Big Activity Data Sources for Robotics \& New Challenges}, year={2018}, address={Madrid, Spain}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/mason_iros_2018.pdf}, abstract={We describe our efforts in developing a Biosignals Acquisition Space and Environment (BASE) to acquire a large database of human everyday activities along with a procedure to automatically structure and label these high-dimensional data into a valuable resource for research in cognitive robotics. The final dataset is planned to consist of synchronously recorded biosignals from about 100 participants performing everyday activities while describing their task through use of think-aloud protocols. Biosignals encompass multimodal sensor streams of near and far speech \& audio, video, marker-based motion tracking, eye-tracking, as well as muscle and brain readings of humans performing everyday activities. This paper provides details of our pilot recordings carried out in the well established and scalable "table setting scenario." Besides presenting initial insights, the paper describes concurrent and retrospective think-aloud protocols and compares their usefulness toward automatic data segmentation and structuring.} } @inproceedings{meier_interspeech_2019, note={Interspeech 2019}, title={Comparative Analysis of Think-aloud Methods for Everyday Activities in the Context of Cognitive Robotics}, year={2019}, month={October}, booktitle={20th Annual Conference of the International Speech Communication Association}, address={Graz, Austria}, author={Meier, Moritz and Mason, Celeste and Putze, Felix and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/meier_interspeech_2019.pdf}, abstract={We describe our efforts to compare data collection methods using two think-aloud protocols in preparation to be used as a basis for automatic structuring and labeling of a large database of high-dimensional human activities data into a valuable resource for research in cognitive robotics. The envisioned dataset, currently in development, will contain synchronously recorded multimodal data, including audio, video, and biosignals (eye-tracking, motion-tracking, muscle and brain activity) from about 100 participants performing everyday activities while describing their task through use of think-aloud protocols. This paper provides details of our pilot recordings in the well-established and scalable ``table setting scenario," describes the concurrent and retrospective think-aloud protocols used, the methods used to analyze them, and compares their potential impact on the data collected as well as the automatic data segmentation and structuring process.} } @inproceedings{putze_augmented_2019, address = {Bari, Italy}, title = {Augmented {Reality} {Interface} for {Smart} {Home} {Control} using {SSVEP}-{BCI} and {Eye} {Gaze}}, booktitle = {{IEEE} {International} {Conference} on {Systems}, {Man}, and {Cybernetics}}, author = {Putze, Felix and Weiß, Dennis and Vortmann, Lisa-Marie and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/putze_ssvep2019.pdf}, year = {2019} } @inproceedings{salous_putze_smc_2019, address = {Bari, Italy}, title = {Visual and Memory-based HCI Obstacles: Behaviour-based Detection and User Interface Adaptations Analysis}, booktitle = {{IEEE} {International} {Conference} on {Systems}, {Man}, and {Cybernetics}}, author = {Salous, Mazen and Putze, Felix and Ihrig, Markus and Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/salous_putze_SMC19.pdf}, year = {2019}, abstract={Human Computer Interaction (HCI) performance can be impaired by several HCI obstacles. Cognitive adaptive systems should dynamically detect such obstacles and compensate them with suitable User Interface (UI) adaptation. In this paper, we discuss the detection of two main HCI obstacles: memory-based and visual obstacles. A sequential model based on Long-Short Term Memory (LSTM) is suggested for such a detection of HCI obstacles. UI adaptations for both types of obstacles are discussed and analyzed. We investigate the classification performance on data from a user study with 17 participants. Furthermore, we also investigate the influence of different adaptation mechanisms on performance and subjective assessment. Results show advantages of the proposed sequential LSTM model: on the one hand, the LSTM outperforms the baseline random guess and also a baseline static model LDA in the detection of visual obstacles with 70.6\% as an average accuracy. On the other hand, the evaluation of HCI sessions impeded by obstacles but supported with different UI adaptations shows that LSTM results well match the subjective assessment as a plausible detector of behaviour changes.} } @article{Tanja_Interspeechkeynote_2019, address = {Graz, Austria}, title = {Biosignal Processing for Human-Machine Interaction. In: Keynote presented at Interspeech 2019, September 2019 Graz, Austria}, year={2019}, month={09}, day={16}, author = {Schultz, Tanja}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Interspeech2019-KeynoteTanjaSchultz.pdf}, abstract={Tanja Schultz held a keynote on "Biosignal Processing for Human-Machine Interaction" at Interspeech 2019, the largest conference on the science and technology of spoken language processing, and flagship of ISCA. Talk on Youtube (https://www.youtube.com/watch?v=XzkQnzP7yPA) Slides for download} } @article{doi:10.1080/2326263X.2019.1697163, author = {Jane E. Huggins and Christoph Guger and Erik Aarnoutse and Brendan Allison and Charles W. Anderson and Steven Bedrick and Walter Besio and Ricardo Chavarriaga and Jennifer L. Collinger and An H. Do and Christian Herff and Matthias Hohmann and Michelle Kinsella and Kyuhwa Lee and Fabien Lotte and Gernot Müller-Putz and Anton Nijholt and Elmar Pels and Betts Peters and Felix Putze and Rüdiger Rupp and Gerwin Schalk and Stephanie Scott and Michael Tangermann and Paul Tubig and Thorsten Zander}, title = {Workshops of the seventh international brain-computer interface meeting: not getting lost in translation}, journal = {Brain-Computer Interfaces}, volume = {0}, number = {0}, pages = {1-31}, year = {2019}, publisher = {Taylor & Francis}, doi = {10.1080/2326263X.2019.1697163}, } @inproceedings{, title = {Towards Restoration of Articulatory Movements: Functional Electrical Stimulation of Orofacial Muscles}, year = {2019}, month = {07}, pages = {3111-3114}, doi = {10.1109/EMBC.2019.8857670} } @inproceedings{schultz_embc_2019, author = {Schultz, Tanja and Angrick, Miguel and Diener, Lorenz and Küster, Dennis and Meier, Moritz and Krusienski, Dean and Herff, Christian and Brumberg, Jonathan}, booktitle={2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)}, title={Towards Restoration of Articulatory Movements: Functional Electrical Stimulation of Orofacial Muscles}, year={2019}, volume={}, number={}, pages={3111-3114}, keywords={brain;muscle;neuromuscular stimulation;speech coding;speech synthesis;decoding speech-related brain activity;physical speech production;decoded speech-related brain activity;eventual orofacial stimulation;functional electrical stimulation;synthesized speech generation;physical speech restoration;electrical stimulation;orofacial muscles stimulation;acoustic production;articulatory movement restoration;Muscles;Production;Electromyography;Spectrogram;Correlation;Electrodes;Brain}, doi={10.1109/EMBC.2019.8857670}, ISSN={1557-170X}, month={July}, abstract={Millions of individuals suffer from impairments that significantly disrupt or completely eliminate their ability to speak. An ideal intervention would restore one's natural ability to physically produce speech. Recent progress has been made in decoding speech-related brain activity to generate synthesized speech. Our vision is to extend these recent advances toward the goal of restoring physical speech production using decoded speech-related brain activity to modulate the electrical stimulation of the orofacial musculature involved in speech. In this pilot study we take a step toward this vision by investigating the feasibility of stimulating orofacial muscles during vocalization in order to alter acoustic production. The results of our study provide necessary foundation for eventual orofacial stimulation controlled directly from decoded speech-related brain activity.}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_fes_embc2019.pdf}, } @inproceedings{weiner2019speech, title={Speech Reveals Future Risk of Developing Dementia: Predictive Dementia Screening from Biographic Interviews}, year={2019}, booktitle={Automatic Speech Recognition and Understanding}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/weiner2019speech.pdf}, author={Weiner, Jochen and Frankenberg, Claudia and Schr\"oder, Johannes and Schultz, Tanja} } @inproceedings{diener2019improving, title={Improving Fundamental Frequency Generation in EMG-to-Speeech Conversion using a Quantization Approach}, year={2019}, booktitle={Automatic Speech Recognition and Understanding}, author={Diener, Lorenz and Umesh, Tejas and and Schultz, Tanja}, abstract={We present a novel approach to generating fundamental frequency (intonation and voicing) trajectories in an EMG-to-Speech conversion Silent Speech Interface, based on quantizing the EMG-to-F0 mappings target values and thus turning a regression problem into a recognition problem. We present this method and evaluate its performance with regard to the accuracy of the voicing information obtained as well as the performance in generating plausible intonation trajectories within voiced sections of the signal. To this end, we also present a new measure for overall F0 trajectory plausibility, the trajectory-label accuracy (TLAcc), and compare it with human evaluations. Our new F0 generation method achieves a significantly better performance than a baseline approach in terms of voicing accuracy, correlation of voiced sections, trajectory-label accuracy and, most importantly, human evaluations.}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/diener_asru_2019_f0_quant.pdf}, } @inproceedings{putze_platform_2020, address = {Honolulu, USA}, title = {Platform for {Studying} {Self}-{Repairing} {Auto}-{Corrections} in {Mobile} {Text} {Entry} based on {Brain} {Activity}, {Gaze}, and {Context}}, booktitle = {Proceedings of the 2020 {CHI} {Conference} on {Human} {Factors} in {Computing} {Systems}}, author = {Putze, Felix and Ihrig, Tilman and Schultz, Tanja and Stuerzlinger, Wolfgang}, year = {2020}, address={Honolulu, USA}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/autocorrect_2020.pdf}, } @inproceedings{putze_breaking_2020, address = {Honolulu, USA}, title = {Breaking {The} {Experience}: {Effects} of {Questionnaires} in {VR} {User} {Studies}}, booktitle = {Proceedings of the 2020 {CHI} {Conference} on {Human} {Factors} in {Computing} {Systems}}, author = {Putze, Susanne and Alexandrovsky, Dmitry and Putze, Felix and Höffner, Sebastian and Smeddinck, Jan David and Malaka, Rainer}, year = {2020}, address={Honolulu, USA}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/chi2020_bip_selfreports.pdf}, } @inproceedings{vortmann_attention-aware_2020, address = {Honolulu, USA}, title = {Attention-{Aware} {Brain} {Computer} {Interface} to avoid {Distractions} in {Augmented} {Reality}}, booktitle = {Proceedings of the 2020 {CHI} {Conference} on {Human} {Factors} in {Computing} {Systems}}, author = {Vortmann, Lisa-Marie and Putze, Felix}, year = {2020}, address={Honolulu, USA}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/vortmann2020attention_aware.pdf}, } @inproceedings{Vortmann2019, abstract = {}, author = {Vortmann, Lisa-Marie and Schult, Moritz and Benedek, Mathias and Walcher, Sonja and Putze, Felix}, doi = { https://doi.org/10.1145/3351529.3360658 }, journal = {Adjunct of the 2019 International Conference on Multimodal Interaction}, title = {{Real-Time Multimodal Classification of Internal and External Attention}}, year = {2019}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/vortmann2019LBW_ICMI.pdf} } @ARTICLE{Vortmann_frontiers2019, AUTHOR={Vortmann, Lisa-Marie and Kroll, Felix and Putze, Felix}, TITLE={EEG-Based Classification of Internally- and Externally-Directed Attention in an Augmented Reality Paradigm}, JOURNAL={Frontiers in Human Neuroscience}, VOLUME={13}, PAGES={348}, YEAR={2019}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/vortmann2019_frontiers.pdf}, DOI={10.3389/fnhum.2019.00348}, ISSN={1662-5161}, ABSTRACT={One problem faced in the design of Augmented Reality (AR) applications is the interference of virtually displayed objects in the user's visual field, with the current attentional focus of the user. Newly generated content can disrupt internal thought processes. If we can detect such internally-directed attention periods, the interruption could either be avoided or even used intentionally. In this work, we designed a special alignment task in AR with two conditions: one with externally-directed attention and one with internally-directed attention. Apart from the direction of attention, the two tasks were identical. During the experiment, we performed a 16-channel EEG recording, which was then used for a binary classification task. Based on selected band power features, we trained a Linear Discriminant Analysis classifier to predict the label for a 13-s window of each trial. Parameter selection, as well as the training of the classifier, were done in a person-dependent manner in a 5-fold cross-validation on the training data. We achieved an average score of approximately 85.37\% accuracy on the test data (± 11.27\%, range = [66.7\%, 100\%], 6 participants > 90\%, 3 participants = 100\%). Our results show that it is possible to discriminate the two states with simple machine learning mechanisms. The analysis of additionally collected data dispels doubts that we classified the difference in movement speed or task load. We conclude that a real-time assessment of internal and external attention in an AR setting in general will be possible.} } @inproceedings{VortmannDC, author = {Vortmann, Lisa-Marie}, title = {Attention-driven Interaction Systems for Augmented Reality}, booktitle = {2019 International Conference on Multimodal Interaction}, series = {ICMI '19}, year = {2019}, isbn = {978-1-4503-6860-5}, location = {Suzhou, China}, pages = {482--486}, numpages = {5}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/vortmann2019DC_ICMI.pdf}, doi = {10.1145/3340555.3356088}, acmid = {3356088}, publisher = {ACM}, address = {New York, NY, USA}, keywords = {adaptive systems, attention, augmented reality, classification, interaction, machine learning, user interface}, } @inproceedings{hartmann2020feature_space, title = {Feature Space Reduction for Multimodal Human Activity Recognition}, author = {Hartmann, Yale and Liu, Hui and Schultz, Tanja}, booktitle = {Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2020) - Volume 4: BIOSIGNALS}, pages = {135--140}, organization = {INSTICC}, publisher = {SCITEPRESS - Science and Technology Publications}, year = {2020}, isbn = {978-989-758-398-8}, issn = {2184-4305}, doi = {10.5220/0008851401350140}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/HartmannLiuSchultz_Biosignals2020.pdf}, abstract = {This work describes the implementation, optimization, and evaluation of a Human Activity Recognition (HAR) system using 21-channel biosignals. These biosignals capture multiple modalities, such as motion and muscle activity based on two 3D-inertial sensors, one 2D-goniometer, and four electromyographic sensors. We start with an early fusion, HMM-based recognition system which discriminates 18 human activities at 91% recognition accuracy. We then optimize preprocessing with a feature space reduction and feature vector stacking. For this purpose, a Linear Discriminant Analysis (LDA) was performed based on HMM state alignments. Our experimental results show that LDA feature space reduction improves recognition accuracy by four percentage points while stacking feature vectors currently does not show any positive effects. To the best of our knowledge, this is the first work on feature space reduction in a HAR system using various biosensors integrated into a knee bandage recognizing a dive rse set of activities.} } @article{barandas2020tsfel, title = {{TSFEL}: {Time} Series Feature Extraction Library}, author = {Barandas, Mar{\'\i}lia and Folgado, Duarte and Fernandes, Let{\'\i}cia and Santos, Sara and Abreu, Mariana and Bota, Patr{\'\i}cia and Liu, Hui and Schultz, Tanja and Gamboa, Hugo}, journal = {SoftwareX}, volume = {11}, pages = {100456}, year = {2020}, publisher = {Elsevier}, doi = {10.1016/j.softx.2020.100456}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/TSFEL_SoftwareX2020.pdf}, abstract = {Time series feature extraction is one of the preliminary steps of conventional machine learning pipelines. Quite often, this process ends being a time consuming and complex task as data scientists must consider a combination between a multitude of domain knowledge factors and coding implementation. We present in this paper a Python package entitled Time Series Feature Extraction Library (TSFEL), which computes over 60 different features extracted across temporal, statistical and spectral domains. User customisation is achieved using either an online interface or a conventional Python package for more flexibility and integration into real deployment scenarios. TSFEL is designed to support the process of fast exploratory data analysis and feature extraction on time series with computational cost evaluation.} } @inproceedings{abulimiti-schultz-2020-automatic, title = "Automatic Speech Recognition for {U}yghur through Multilingual Acoustic Modeling", author = "Abulimiti, Ayimunishagu and Schultz, Tanja", booktitle = "Proceedings of The 12th Language Resources and Evaluation Conference", month = may, year = "2020", address = "Marseille, France", publisher = "European Language Resources Association", url = "https://www.csl.uni-bremen.de/cms/images/documents/publications/ay_LREC2020.pdf", pages = "6444--6449", abstract = "Low-resource languages suffer from lower performance of Automatic Speech Recognition (ASR) system due to the lack of data. As a common approach, multilingual training has been applied to achieve more context coverage and has shown better performance over the monolingual training (Heigold et al., 2013). However, the difference between the donor language and the target language may distort the acoustic model trained with multilingual data, especially when much larger amount of data from donor languages is used for training the models of low-resource language. This paper presents our effort towards improving the performance of ASR system for the under-resourced Uyghur language with multilingual acoustic training. For the developing of multilingual speech recognition system for Uyghur, we used Turkish as donor language, which we selected from GlobalPhone corpus as the most similar language to Uyghur. By generating subsets of Uyghur training data, we explored the performance of multilingual speech recognition systems trained with different sizes of Uyghur and Turkish data. The best speech recognition system for Uyghur is achieved by multilingual training using all Uyghur data (10hours) and 17 hours of Turkish data and the WER is 19.17{\%}, which corresponds to 4.95{\%} relative improvement over monolingual training.", language = "English", ISBN = "979-10-95546-34-4", } @inproceedings{abulimiti-schultz-2020-building, title = "Building Language Models for Morphological Rich Low-Resource Languages using Data from Related Donor Languages: the Case of {U}yghur", author = "Abulimiti, Ayimunishagu and Schultz, Tanja", booktitle = "Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)", month = may, year = "2020", address = "Marseille, France", publisher = "European Language Resources association", url = "https://www.csl.uni-bremen.de/cms/images/documents/publications/ay_SLTU2020.pdf", pages = "271--276", abstract = "Huge amounts of data are needed to build reliable statistical language models. Automatic speech processing tasks in low-resource languages typically suffer from lower performances due to weak or unreliable language models. Furthermore, language modeling for agglutinative languages is very challenging, as the morphological richness results in higher Out Of Vocabulary (OOV) rate. In this work, we show our effort to build word-based as well as morpheme-based language models for Uyghur, a language that combines both challenges, i.e. it is a low-resource and agglutinative language. Fortunately, there exists a closely-related rich-resource language, namely Turkish. Here, we present our work on leveraging Turkish text data to improve Uyghur language models. To maximize the overlap between Uyghur and Turkish words, the Turkish data is pre-processed on the word surface level, which results in 7.76{\%} OOV-rate reduction on the Uyghur development set. To investigate various levels of low-resource conditions, different subsets of Uyghur data are generated. Morpheme-based language models trained with bilingual data achieved up to 40.91{\%} relative perplexity reduction over the language models trained only with Uyghur data.", language = "English", ISBN = "979-10-95546-35-1", } @INPROCEEDINGS{9053144, author={M. Y. {Tachbelie} and A. {Abulimiti} and S. T. {Abate} and T. {Schultz}}, booktitle={ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, title={DNN-Based Speech Recognition for Globalphone Languages}, year={2020}, volume={}, number={}, pages={8269-8273}, abstract={This paper describes new reference benchmark results based on hybrid Hidden Markov Model and Deep Neural Networks (HMM-DNN) for the GlobalPhone (GP) multilingual text and speech database. GP is a multilingual database of high-quality read speech with corresponding transcriptions and pronunciation dictionaries in more than 20 languages. Moreover, we provide new results for five additional languages, namely, Amharic, Oromo, Tigrigna, Wolaytta, and Uyghur. Across the 22 languages considered, the hybrid HMM-DNN models outperform the HMM-GMM based models regardless of the size of the training speech used. Overall, we achieved relative improvements that range from 7.14% to 59.43%.}, keywords={GlobalPhone;DNN;Ethiopian Languages}, doi={10.1109/ICASSP40776.2020.9053144}, ISSN={2379-190X}, month={May}, url = "https://www.csl.uni-bremen.de/cms/images/documents/publications/martha_ICASSP2020.pdf", } @inproceedings{diener2020cslemgarray, title={{CSL-EMG\_Array: An Open Access Corpus for EMG-to-Speech Conversion}}, author={Diener, Lorenz and Roustay Vishkasougheh, Mehrdad and Schultz, Tanja}, booktitle={{INTERSPEECH} 2020 - 21st Annual Conference of the International Speech Communication Association}, year={2020 (to appear)}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Diener_IS2020_CSLEMGArray.pdf}, abstract={We present a new open access corpus for the training and evaluation of EMG-to-Speech conversion systems based on array electromyographic recordings. The corpus is recorded with a recording paradigm closely mirroring realistic EMG-to-Speech usage scenarios, and includes evaluation data recorded from both audible as well as silent speech. The corpus consists of 9.5 hours of data, split into 12 sessions recorded from 8 speakers. Based on this corpus, we present initial benchmark results with a realistic online EMG-to-Speech conversion use case, both for the audible and silent speech subsets. We also present a method for drastically improving EMG-to-Speech system stability and performance in the presence of time-related artifacts.}, } @inproceedings{diener2020towards, title={Towards Silent Paralinguistics: Deriving Speaking Mode and Speaker ID from Electromyographic Signals}, author={Diener, Lorenz and Amiriparian, Shahin and Botelho, Catarina and Scheck, Kevin and Küster, Dennis and Trancoso, Isabel Schuller, Björn W. and Schultz, Tanja}, booktitle={{INTERSPEECH} 2020 - 21st Annual Conference of the International Speech Communication Association}, year={2020 (to appear)}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Diener_IS2020_SilentCompPara.pdf}, abstract={Silent Computational Paralinguistics (SCP) - the assessment of speaker states and traits from non-audibly spoken communication - has rarely been targeted in the rich body of either Computational Paralinguistics or Silent Speech Processing. Here, we provide first steps towards this challenging but potentially highly rewarding endeavour: Paralinguistics can enrich spoken language interfaces, while Silent Speech Processing enables confidential and unobtrusive spoken communication for everybody, including mute speakers. We approach SCP by using speech-related biosignals stemming from facial muscle activities captured by surface electromyography (EMG). To demonstrate the feasibility of SCP, we select one speaker trait (speaker identity) and one speaker state (speaking mode). We introduce two promising strategies for SCP: (1) deriving paralinguistic speaker information directly from EMG of silently produced speech versus (2) first converting EMG into an audible speech signal followed by conventional computational paralinguistic methods. We compare traditional feature extraction and decision making approaches to more recent deep representation and transfer learning by convolutional and recurrent neural networks, using openly available EMG data. We find that paralinguistics can be assessed not only from acoustic speech but also from silent speech captured by EMG.}, } @inproceedings{botelho2020towards, title={Toward Silent Paralinguistics: Speech-to-EMG - Retrieving Articulatory Muscle Activity from Speech}, author={Botelho, Catarina and Diener, Lorenz and Küster, Dennis and Scheck, Kevin and Amiriparian, Shahin and Schuller, Björn W. and Schultz, Tanja and Abad, Alberto and Trancoso, Isabel}, booktitle={{INTERSPEECH} 2020 - 21st Annual Conference of the International Speech Communication Association}, year={2020 (to appear)}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Interspeech2020_emg_to_speech_revised.pdf}, abstract={Electromyographic (EMG) signals recorded during speech production encode information on articulatory muscle activity and also on the facial expression of emotion, thus representing a speech-related biosignal with strong potential for paralinguistic applications. In this work, we estimate the electrical activity of the muscles responsible for speech articulation directly from the speech signal. To this end, we first perform a neural conversion of speech features into electromyographic time domain features, and then attempt to retrieve the original EMG signal from the time domain features. We propose a feed forward neural network to address the first step of the problem (speech features to EMG features) and a neural network composed of a convolutional block and a bidirectional long short-term memory block to address the second problem (true EMG features to EMG signal). We observe that four out of the five originally proposed time domain features can be estimated reasonably well from the speech signal. Further, the five time domain features are able to predict the original speech-related EMG signal with a concordance correlation coefficient of 0.663. We further compare our results with the ones achieved on the inverse problem of generating acoustic speech features from EMG features.}, } @inproceedings{mason_iros2020, title = {From Human to Robot Everyday Activity}, author = {Mason, Celeste and Gadzicki, Konrad and Meier, Moritz and Ahrens, Florian and Kluss, Thorsten and Maldonado, Jaime and Putze, Felix and Fehr, Thorsten and Zetzsche, Christoph and Herrmann, Manfred and Schill, Kerstin and Schultz, Tanja}, booktitle = {IROS 2020}, year = {2020}, url={ https://www.csl.uni-bremen.de/cms/images/documents/publications/mason_iros2020.pdf }, address={Las Vegas, USA}, abstract={The Everyday Activities Science and Engineering (EASE) Collaborative Research Consortium's mission to enhance the performance of cognition-enabled robots establishes its foundation in the EASE Human Activities Data Analysis Pipeline. Through collection of diverse human activity information resources, enrichment with contextually relevant annotations, and subsequent multimodal analysis of the combined data sources, the pipeline described will provide a rich resource for robot planning researchers, through incorporation in the OpenEASE cloud platform.} } @inproceedings{angrick2020speech, title={Speech Spectrogram Estimation from Intracranial Brain Activity using a Quantization Approach}, author={Angrick, Miguel and Herff, Christian and Johnson, Garett and Shih, Jerry and Krusienski, Dean and Schultz, Tanja}, note={Interspeech 2020}, abstract={Direct synthesis from intracranial brain activity into acoustic speech might provide an intuitive and natural communication means for speech-impaired users. In previous studies we have used logarithmic Mel-scaled speech spectrograms (logMels) as an intermediate representation in the decoding from ElectroCorticoGraphic (ECoG) recordings to an audible waveform. Mel-scaled speech spectrograms have a long tradition in acoustic speech processing and speech synthesis applications. In the past, we relied on regression approaches to find a mapping from brain activity to logMel spectral coefficients, due to the continuous feature space. However, regression tasks are unbounded and thus neuronal fluctuations in brain activity may result in abnormally high amplitudes in a synthesized acoustic speech signal. To mitigate these issues, we propose two methods for quantization of power values to discretize the feature space of logarithmic Mel-scaled spectral coefficients by using the median and the logistic formula, respectively, to reduce the complexity and restricting the number of intervals. We evaluate the practicability in a proof-of-concept with one participant through a simple classification based on linear discriminant analysis and compare the resulting waveform with the original speech. Reconstructed spectrograms achieve Pearson correlation coefficients with a mean of r=0.5 ± 0.11 in a 5-fold cross validation.}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/angrick2020speech.pdf}, keywords={neural signals for spoken communication, speech synthesis, electrocorticography, BCI}, year={2020} } @article{kuster_i_2020, title = {I saw it on {YouTube}! {How} online videos shape perceptions of mind, morality, and fears about robots}, issn = {1461-4448, 1461-7315}, url= {https://www.csl.uni-bremen.de/cms/images/documents/publications/Kuster_et_al_I_saw_it_on_YouTube.pdf}, doi = {10.1177/1461444820954199}, abstract = {Robots have the potential to transform our existing categorical distinctions between “property” and “persons.” Previous research has demonstrated that humans naturally anthropomorphize them, and this tendency may be amplified when a robot is subject to abuse. Simultaneously, robots give rise to hopes and fears about the future and our place in it. However, most available evidence on these mechanisms is either anecdotal, or based on a small number of laboratory studies with limited ecological validity. The present work aims to bridge this gap through examining responses of participants (N = 160) to four popular online videos of a leading robotics company (Boston Dynamics) and one more familiar vacuum cleaning robot (Roomba). Our results suggest that unexpectedly human-like abilities might provide more potent cues to mind perception than appearance, whereas appearance may attract more compassion and protection. Exposure to advanced robots significantly influences attitudes toward future artificial intelligence. We discuss the need for more research examining groundbreaking robotics outside the laboratory.}, language = {en}, urldate = {2020-09-21}, journal = {New Media \& Society}, author = {Küster, Dennis and Swiderska, Aleksandra and Gunkel, David}, month = sep, year = {2020}, pages = {146144482095419} } @article{kuster_seeing_2020, title = {Seeing the mind of robots: Harm augments mind perception but benevolent intentions reduce dehumanisation of artificial entities in visual vignettes}, language = {en}, author = {Küster, Dennis and Swiderska, Aleksandra}, url= {https://www.csl.uni-bremen.de/cms/images/documents/publications/Kuster_Swiderska_2020_Seeing_the_mind_of_robots.pdf}, doi= {10.1002/ijop.12715}, abstract = {According to moral typecasting theory, good‐ and evil‐doers (agents) interact with the recipients of their actions (patients) in a moral dyad. When this dyad is completed, mind attribution towards intentionally harmed liminal minds is enhanced. However, from a dehumanisation view, malevolent actions may instead result in a denial of humanness. To contrast both accounts, a visual vignette experiment (N = 253) depicted either malevolent or benevolent intentions towards robotic or human avatars. Additionally, we examined the role of harm‐salience by showing patients as either harmed, or still unharmed. The results revealed significantly increased mind attribution towards visibly harmed patients, mediated by perceived pain and expressed empathy. Benevolent and malevolent intentions were evaluated respectively as morally right or wrong, but their impact on the patient was diminished for the robotic avatar. Contrary to dehumanisation predictions, our manipulation of intentions failed to affect mind perception. Nonetheless, benevolent intentions reduced dehumanisation of the patients. Moreover, when pain and empathy were statistically controlled, the effect of intentions on mind perception was mediated by dehumanisation. These findings suggest that perceived intentions might only be indirectly tied to mind perception, and that their role may be better understood when additionally accounting for empathy and dehumanisation.}, journal = {International Journal of Psychology}, year = {2020}, pages = {12} } @article{swiderska_robots_2020, title = {Robots as malevolent moral agents: Harmful behavior results in dehumanization, not anthropomorphism}, volume = {44}, issn = {0364-0213, 1551-6709}, shorttitle = {Robots as malevolent moral agents}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/Swiderska_Kuester_RobotsAsMalevolentAgents_CognitiveScience_PrePrintVersion.pdf}, doi = {10.1111/cogs.12872}, abstract = {A robot’s decision to harm a person is sometimes considered to be the ultimate proof of it gaining a human-like mind. Here, we contrasted predictions about attribution of mental capacities from moral typecasting theory, with the denial of agency from dehumanization literature. Experiments 1 and 2 investigated mind perception for intentionally and accidentally harmful robotic agents based on text and image vignettes. Experiment 3 disambiguated agent intention (malevolent and benevolent), and additionally varied the type of agent (robotic and human) using short computer-generated animations. Harmful robotic agents were consistently imbued with mental states to a lower degree than benevolent agents, supporting the dehumanization account. Further results revealed that a human moral patient appeared to suffer less when depicted with a robotic agent than with another human. The findings suggest that future robots may become subject to humanlike dehumanization mechanisms, which challenges the established beliefs about anthropomorphism in the domain of moral interactions.}, language = {en}, number = {7}, urldate = {2020-09-21}, journal = {Cognitive Science}, author = {Swiderska, Aleksandra and Küster, Dennis}, month = jul, year = {2020} } @article{dupre_performance_2020, title = {A performance comparison of eight commercially available automatic classifiers for facial affect recognition}, volume = {15}, issn = {1932-6203}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/Dupre_et_al_2020_A_performance_comparison_of_eight_commercially_available_automatic_classifiers.pdf}, doi = {10.1371/journal.pone.0231968}, language = {en}, number = {4}, urldate = {2020-09-21}, journal = {PLOS ONE}, author = {Dupré, Damien and Krumhuber, Eva G. and Küster, Dennis and McKeown, Gary J.}, editor = {D’Mello, Sidney}, month = apr, year = {2020}, pages = {e0231968} } @incollection{kuster_hidden_2020, address = {Cham}, title = {Hidden tears and scrambled joy: On the adaptive costs of unguarded nonverbal social signals}, isbn = {978-3-030-34964-6}, shorttitle = {Hidden tears and scrambled joy}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/Kuester_HiddenTears_PrePrint.pdf}, abstract = {The ability to correctly assess the internal states of another is assumed to have clear adaptive advantages. Yet, the balance of evolutionary costs and benefits appears less obvious for the sender. Rather than to indiscriminately maximize the ratio of signal to noise, human nonverbal signaling is finely tuned to its situational context. We smile naturally and without flinching, out of politeness, to signal positive intentions, or to distract an opponent. Careless displays of fear may draw a predator’s attention, or they may reveal a readiness to abandon resources without a fight. Emotional tears result in blurred vision and reduce visual acuity, akin to a self-imposed handicap. This chapter re-examines socially intelligent nonverbal communication while focusing on the evolutionary costs of signaling too clearly and indiscriminately.}, language = {en}, urldate = {2020-09-21}, booktitle = {Social {Intelligence} and {Nonverbal} {Communication}}, publisher = {Springer International Publishing}, author = {Küster, Dennis}, editor = {Sternberg, Robert J. and Kostić, Aleksandra}, year = {2020}, doi = {10.1007/978-3-030-34964-6_10}, keywords = {Adaptive costs, Display rules, Emotional tears, Nonverbal social signals, Social intelligence}, pages = {283--304} } @article{kuster_opportunities_2020, title = {Opportunities and challenges for using automatic human affect analysis in consumer research}, volume = {14}, issn = {1662-453X}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/Kuster_et_al_2020_Opportunities_and_Challenges_for_Using_Automatic_Human_Affect_Analysis_in.pdf}, doi = {10.3389/fnins.2020.00400}, language = {en}, urldate = {2020-09-21}, journal = {Frontiers in Neuroscience}, author = {Küster, Dennis and Krumhuber, Eva G. and Steinert, Lars and Ahuja, Anuj and Baker, Marc and Schultz, Tanja}, month = apr, year = {2020}, pages = {400} } @inproceedings{najafabadi_tool-use_2020, title = {Tool-use training in augmented reality: Changes on forearm body schema and somatosensory representation}, booktitle={FENS International Conference 2020}, abstract = {Body Miller et al. (2014) described altered arm representation and body schema after training to use a mechanical gripper for grasping distant objects. We examined whether similar training with a virtual tool in augmented reality (AR) would have comparable effects. Thirty young adults learned controlling a virtual gripper to grasp virtual objects at various locations in horizontal plane. Vibrotactile feedback was applied to thumb and index fingers through a CyberTouch II cyber glove when the tool touched the object. Participants performed 4 training blocks with 60 trials each. In a tactile distance judgement task performed before, after 2 blocks, and after 4 blocks of training, participants judged distances between two tactile stimuli, synchronously applied to their right forearm. The stimuli were applied either along (“vertical”) or perpendicular (“horizontal”) to the arm, with three distances per orientation (5 trials per orientation and distance). Mean estimation errors were calculated. ANCOVA with orientation as factor and estimation error at t0 as covariate to correct for baseline differences, revealed a significant effect of orientation (F(1,375) = 4.1156, p = .043, pEta² = .011). Estimation errors were smaller for vertical as compared to horizontal orientations, indicating that the stimulated locations on the arm were perceived as being closer together for the vertical orientation. These results confirm that virtual tool use training has a strong short-term effect on the body schema. We conclude that the virtual tool was integrated into the arm representation resulting in a shrinkage of perceived distances on the arm along the vertical axis.}, language = {en}, author = {Jahanian Najafabadi, Amir and Putze, Felix and Küster, Dennis and Hunter, Mathew and Godde, Ben}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/Najafabadi_Tool-use2020.pdf}, location = {Glasgow, UK}, month = jul, year = {2020}, pages = {} } @inproceedings{dente2017measures, title={Measures and metrics for automatic emotion classification via FACET}, abstract = {For dynamic emotions to be modelled in a natural and convincing way, systems must rely on accurate affective analysis of facial expressions in the first place. The present work introduces two measures for evaluating automatic emotion classification performance. It further provides a systematic comparison between 14 databases of dynamic expressions. Machine analysis was conducted using the FACET system, with an algorithm calculating recognition sensitivity and confidence. Results revealed the proportion of facial stimuli that could be recognised by the machine algorithm above threshold evidence, showing significant differences in recognition performance between the databases.}, author={Dente, Pasquale and K{\"u}ster, Dennis and Skora, Lina and Krumhuber, E}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/Dente_et_al_2017_Measures_and_metrics_for_automatic_emotion_classif.pdf}, booktitle={Proceedings of the Conference on the Study of Artificial Intelligence and Simulation of Behaviour (AISB)}, pages={160--163}, year={2017} } @inproceedings{10.1145/3382507.3418856, author = {Steinert, Lars and Putze, Felix and K\"{u}ster, Dennis and Schultz, Tanja}, title = {Towards Engagement Recognition of People with Dementia in Care Settings}, year = {2020}, isbn = {9781450375818}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3382507.3418856}, doi = {10.1145/3382507.3418856}, abstract = {Roughly 50 million people worldwide are currently suffering from dementia. This number is expected to triple by 2050. Dementia is characterized by a loss of cognitive function and changes in behaviour. This includes memory, language skills, and the ability to focus and pay attention. However, it has been shown that secondary therapy such as the physical, social and cognitive activation of People with Dementia (PwD) has significant positive effects. Activation impacts cognitive functioning and can help prevent the magnification of apathy, boredom, depression, and loneliness associated with dementia. Furthermore, activation can lead to higher perceived quality of life. We follow Cohen's argument that activation stimuli have to produce engagement to take effect and adopt his definition of engagement as "the act of being occupied or involved with an external stimulus".}, booktitle = {Proceedings of the 2020 International Conference on Multimodal Interaction}, pages = {558–565}, numpages = {8}, keywords = {dementia, engagement, lstm, emotion, facial expressions}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/Steinert_ICMI2020_TowardsEngagement.pdf}, location = {Virtual Event, Netherlands}, series = {ICMI '20} } @article{10.1371/journal.pone.0208119, author = {Steinert, Lars AND Herff, Christian}, journal = {PLOS ONE}, publisher = {Public Library of Science}, title = {Predicting altcoin returns using social media}, year = {2018}, month = {12}, volume = {13}, url = {https://doi.org/10.1371/journal.pone.0208119}, pages = {1-12}, abstract = {Cryptocurrencies have recently received large media interest. Especially the great fluctuations in price have attracted such attention. Behavioral sciences and related scientific literature provide evidence that there is a close relationship between social media and price fluctuations of cryptocurrencies. This particularly applies to smaller currencies, which can be substantially influenced by references on Twitter. Although these so-called “altcoins” often have smaller trading volumes they sometimes attract large attention on social media. Here, we show that fluctuations in altcoins can be predicted from social media. In order to do this, we collected a dataset containing prices and the social media activity of 181 altcoins in the form of 426,520 tweets over a timeframe of 71 days. The containing public mood was then estimated using sentiment analysis. To predict altcoin returns, we carried out linear regression analyses based on 45 days of data. We showed that short-term returns can be predicted from activity and sentiments on Twitter.}, number = {12}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/Steinert_journal.pone.0208119.pdf}, doi = {10.1371/journal.pone.0208119} } @article{abulimiti2020automatic, title={Automatic Speech Recognition for ILSE-Interviews: Longitudinal Conversational Speech Recordings covering Aging and Cognitive Decline}, author={Abulimiti, Ayimunishagu and Weiner, Jochen and Schultz, Tanja}, journal={Proc. Interspeech 2020}, pages={3795--3799}, year={2020}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/ay_interspeech2020.pdf}, abstract ={The \textit{Interdisciplinary Longitudinal Study on Adult Development and Aging} (ILSE) was initiated with the aim to investigate satisfying and healthy aging. Over 20 years, about 4200 hours of biographic interviews from more than 1,000 participants were recorded. Spoken language is a strong indicator for declining cognitive resources, as it is affected in early stage. Hence, various research topics related to aging like dementia, could be analyzed based on data such as the ILSE interviews. The analysis of language capabilities requires transcribed speech. Since manual transcriptions are time and cost consuming, we aim to automatically transcribing the ILSE data using Automatic Speech Recognition (ASR). The recognition of ILSE interviews is very demanding due to the combination of various challenges: 20 year old analog two-speaker one-channel recordings of low signal quality, emotional and personal interviews between doctor and participant, and repeated recordings of aging, partly fragile individuals. In this study, we describe ongoing work to develop hybrid Hidden Markov Model (HMM)- Deep Neural Network (DNN) based ASR system for the ILSE corpus. So far, the best ASR system is obtained by second-pass decoding of a hybrid HMM-DNN model using recurrent neural network based language models with a word error rate of $50.39$\%. %Interdisciplinary Longitudinal Study on Adult Development} (ILSE) was initiated with the aim to investigate satisfying and healthy aging. ILSE contains over 4200 hours of biographic interviews with more than 1,000 participants. } } @inproceedings{hartmann2021featurespace, title = {Feature Space Reduction for Human Activity Recognition Based on Multi-channel Biosignals}, author = {Hartmann, Yale and Liu, Hui and Schultz, Tanja}, booktitle = {Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2021) - Volume 4: BIOSIGNALS}, pages = {215--222}, organization = {INSTICC}, publisher = {SCITEPRESS - Science and Technology Publications}, year = {2021}, isbn = {978-989-758-490-9}, issn = {2184-4305}, doi = {10.5220/0010260802150222}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/HartmannLiuSchultz_Biosignals2021.pdf}, abstract = {In this paper, we study the effect of Feature Space Reduction for the task of Human Activity Recognition (HAR). For this purpose, we investigate a Linear Discriminant Analysis (LDA) trained with Hidden Markov Models (HMMs) force-aligned targets. HAR is a typical application of machine learning, which includes finding a lower-dimensional representation of sequential data to address the curse of dimensionality. This paper uses three datasets (CSL19, UniMiB, and CSL18), which contain data recordings from humans performing more than 16 everyday activities. Data were recorded with wearable sensors integrated into two devices, a knee bandage and a smartphone. First, early-fusion baselines are trained, utilizing an HMM-based approach with Gaussian Mixture Models to model the emission probabilities. Then, recognizers with feature space reduction based on stacking combined with an LDA are evaluated and compared against the baseline. Experimental results show that feature space reduction improves balanced accuracy by ten percentage points on the UniMiB and seven points on the CSL18 datasets while remaining the same on the CSL19 dataset. The best recognizers achieve 93.7 ± 1.4{\%} (CSL19), 69.5 ± 8.1{\%} (UniMiB), and 70.6 ± 6.0{\%} (CSL18) balanced accuracy in a leave-one-person-out cross-validation.} } @article{schultz2021lablinking, abstract = {We introduce the concept of LabLinking: a technology-based interconnection of experimental laboratories across institutions, disciplines, cultures, languages, and timezones - in other wordsexperiments without borders. In particular, we introduceLabLinking levels (LLL), which define the degree of tightness of empirical interconnection between labs. We describe the technological infrastructure in terms of hard- and software required for the respective LLLs and present examples of linked laboratories along with insights about the challenges and benefits. In sum, we argue that linked labs provide a unique platform for a continuous exchange between scientists and experimenters, thereby enabling a time synchronous execution of experiments performed with and by decentralized user and researchers, improving outreach and ease of subject recruitment, allowing to establish new experimental designs and to incorporate a panoply of complementary biosensors, devices, hard- and software solutions.}, author = {Schultz, Tanja and Putze, Felix and Fehr, Thorsten and Meier, Moritz and Mason, Celeste and Ahrens, Florian and Herrmann, Manfred}, doi = {10.1101/2021.02.09.430407 }, keywords = {Biosignals,LabLinking}, journal = {bioRxiv}, publisher = {Cold Spring Harbor Laboratory}, title = {Linking Labs: Interconnecting Experimental Environments}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/schultz_lablinking_2021.pdf}, year = {2021} } @article{gracanin_how_2021, title = {How {Weeping} {Influences} the {Perception} of {Facial} {Expressions}: {The} {Signal} {Value} of {Tears}}, volume = {45}, issn = {1573-3653}, url = {https://doi.org/10.1007/s10919-020-00347-x}, doi = {10.1007/s10919-020-00347-x}, abstract = {Emotional tears have been proposed to serve as a signal of distress, appeasement, and helplessness, which promotes prosocial responses in observers. They may also facilitate the perception of sadness. A still unanswered question is what information tears convey about emotional states when they are combined with different muscular facial expressions. The current study evaluated three hypotheses: Tears facilitate inferences about (a) emotion intensity in general (b) sadness in particular, or (c) helplessness-related appraisal and behavioral intentions. In the first experiment, participants viewed pictures of (non)tearful real and artificial faces displaying anger, disgust, fear, happiness, sadness, surprise, and neutral state. They had to report which of the seven expressions they recognized, and to rate its intensity, sincerity, and felt empathy. Tears appeared to facilitate the perception of sadness, but also of anger and fear, while they decreased the perception of disgust and surprise. The ratings of the intensity, the perceived sincerity, and the experienced empathy followed a similar pattern. In the second experiment, participants had to indicate if briefly (50 ms) presented (non)tearful faces showed a particular expression, and we measured their accuracy and reaction times. The results of the first experiment were not corroborated. Overall, the findings lend most support to the appraisal/behavioral intentions hypothesis and less support for the intensity and the sadness enhancement hypotheses.}, number = {1}, journal = {Journal of Nonverbal Behavior}, author = {Gračanin, Asmir and Krahmer, Emiel and Balsters, Martijn and Küster, Dennis and Vingerhoets, Ad J. J. M.}, month = mar, year = {2021}, pages = {83--105}, } @phdthesis{salous2021thesis, school={University of Bremen}, title={User Modeling for Adaptation of Cognitive Systems}, year={2021}, supervisor={Schultz, Tanja and von Helversen, Bettina and Putze, Felix}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Salous2021Diss.pdf}, author={Salous, Mazen} } @phdthesis{diener2021thesis, school={University of Bremen}, title={The Impact of Audible Feedback on EMG-to-Speech Conversion}, year={2021}, supervisor={Schultz, Tanja and Hueber, Thomas}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Diener2021Diss.pdf}, author={Diener, Lorenz} } @inproceedings{borsdorf2021GlobalPhoneMS2, title={{GlobalPhone Mix-to-Separate out of 2: A Multilingual 2000 Speakers Mixtures Database for Speech Separation}}, author={Borsdorf, Marvin and Xu, Chenglin and Li, Haizhou and Schultz, Tanja}, booktitle={{Proceedings of the 22nd Annual Conference of the International Speech Communication Association (INTERSPEECH)}}, year={2021}, pages={3905--3909}, doi={10.21437/Interspeech.2021-1552}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Borsdorf2021GlobalPhoneMS2.pdf}, abstract={Monaural speech separation has been well studied on various databases. However, these databases mostly concern English speech. Research in multi-speaker scenarios, such as speech recognition, speaker recognition, speaker diarization, and speech separation calls for speaker mixtures databases comprising multiple languages. In this paper, we propose a new extensive multilingual database for speech separation tasks derived from the GlobalPhone 2000 Speaker Package, called "GlobalPhone Mix-to-Separate out of 2" (GlobalPhoneMS2). We describe the construction of the database and conduct speech separation experiments in monolingual and multilingual as well as seen and unseen languages settings. When trained on a multilingual dataset, the networks improve their performances for unseen languages, and across almost all seen languages. We show that replacing a monolingual dataset with a trilingual one, while keeping the data size roughly the same, helps to improve the performance in most cases. We attribute this to a larger diversity in speech, language, speaker, and recording characteristics. Based on the GlobalPhoneMS2 database, speech separation results for two-speaker mixing scenarios are reported in 22 spoken languages for the first time.}, } @inproceedings{borsdorf2021UniversalSpeakerExtraction, title={{Universal Speaker Extraction in the Presence and Absence of Target Speakers for Speech of One and Two Talkers}}, author={Borsdorf, Marvin and Xu, Chenglin and Li, Haizhou and Schultz, Tanja}, booktitle={{Proceedings of the 22nd Annual Conference of the International Speech Communication Association (INTERSPEECH)}}, year={2021}, pages={1469--1473}, doi={10.21437/Interspeech.2021-1939}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Borsdorf2021UniversalSpeakerExtraction.pdf}, abstract={Speaker extraction has been studied mostly for the scenarios where a target speaker is present in a two or more talkers mixture. Such scenarios do not adequately reflect everyday conversations. For example, a target speaker can be the only active talker, be quiet for a while, or leave the conversation, that means the target speaker is absent from the mixture. Traditional speaker extraction models fail in these scenarios. We propose a novel speaker extraction approach to handle speech mixtures with one or two talkers in which the target speaker can either be present or absent. First, we formulate four speaker extraction conditions to cover the typical scenarios of everyday conversations with one and two talkers. Second, we introduce a joint training scheme with one unified loss function that works for all four conditions. We show that only a small amount of data is required to adapt the model to work well in the four conditions.}, } @inproceedings{borsdorf2021TargetLanguageExtraction, title={Target Language Extraction at Multilingual Cocktail Parties}, author={Borsdorf, Marvin and Li, Haizhou and Schultz, Tanja}, booktitle={2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)}, year={2021}, pages={717--724}, doi={10.1109/ASRU51503.2021.9688052}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Borsdorf2021TargetLanguageExtraction.pdf}, abstract={Typically, target speaker extraction seeks to extract a target speaker's contribution according to his or her individual voice characteristics. In a "multilingual cocktail party" however, listeners may desire to extract speaker contributions spoken in a particular language, regardless of the number of contributing speakers. In this paper, we propose a novel task called "target language extraction" (TLE) which extracts voices based on the spoken language rather than on individual speaker characteristics. We introduce a new database for TLE which simulates the multilingual cocktail party problem in mixtures of two and four speakers with German as the target language. The database is derived from the GlobalPhone 2000 Speaker Package and is called "GlobalPhone Multilingual Cocktail Party - German" (GlobalPhoneMCP-GE). Our experimental results show that our approach to TLE achieves very good performance regardless of the number of speakers in the mixture and that TLE generalizes well to unseen speakers and interfering languages. This work represents the first attempt at target language extraction.}, } @inproceedings{ablimitITG2021, title={{Automatic Speech Recognition for Dementia Screening using ILSE-Interviews}}, author={Ayimnisagul Ablimit and Tanja Schultz}, booktitle={14th ITG Conference on Speech Communication}, year={2021}, abstract={Spoken language skills are strong biomarkers for detecting cognitive decline. Studies like the Interdisciplinary Longitudinal Study of Adult Development and Aging (ILSE) are of particular interest to quantify the predictive power of biomarkers in terms of acoustic/linguistic features. ILSE consists of ca. 6500 hours of interviews and only $10\%$ were manually transcribed. To extract linguistic features, we need to build reliable ASR to provide transcriptions. The ILSE-corpus is challenging for ASR, due to a combination of factors. In this study, we present our effort to overcome some of these challenges. We automatically segmented 45-minutes of interviews into shorter segments and time aligned. Using these segments, we developed HMM-DNN based ASR and achieved $33.55\%$ of WER. Based on this system, we recreated the time-alignments for manual-transcriptions and derived acoustic and linguistic features for classifier-training. we applied the resulting system for dementia screening and achieved UAR of $0.867$ for a three-class problem.}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ay_ITG2021.pdf}, } @inproceedings{liu2021motion_units, title = {{Motion Units}: {Generalized} Sequence Modeling of Human Activities for Sensor-Based Activity Recognition}, author = {Liu, Hui and Hartmann, Yale and Schultz, Tanja}, booktitle = {29th European Signal Processing Conference (EUSIPCO 2021)}, year = {2021}, pages={1506-1510}, organization = {IEEE}, doi = {10.23919/EUSIPCO54536.2021.9616298}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/LiuHartmannSchultz_EUSIPCO2021.pdf}, abstract = {This paper proposes an innovative activity modeling method for human activity recognition, which partitions the human activity into a sequence of shared, meaningful, and activity distinguishing states, called Motion Units, analog to phonemes in speech recognition. The partitions and generalization define a human activity dictionary, which endows this method with operability, universality, and expandability. Our preliminary experiments demonstrate on-par accuracy with other models while requiring fewer parameters and increasing separability between phases. Furthermore, the developed model was easily transferred with minor adjustments to two other datasets, demonstrating the proposed method's scalability. This framework enables expandable, interpretable, and scaleable modeling and recognition of human activities.} } @article{liu2021cslshare, title = {{CSL-SHARE}: {A} Multimodal Wearable Sensor-Based Human Activity Dataset}, author = {Liu, Hui and Hartmann, Yale and Schultz, Tanja}, journal = {Frontiers in Computer Science}, volume = {3}, article-number = {759136}, year = {2021}, doi = {10.3389/fcomp.2021.759136}, publisher = {Frontiers Media SA}, issn = {2624-9898}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/LiuHartmannSchultz_Frontiers2021.pdf} } @phdthesis{liu2021thesis, school = {University of Bremen}, title = {Biosignal Processing and Activity Modeling for Multimodal Human Activity Recognition}, year = {2021}, supervisor = {Schultz, Tanja and Gamboa, Hugo}, author = {Liu, Hui}, keywords = {Human activity recognition; Motion units; Hidden Markov models; Pattern Recognition; Accelerometer; Gyroscope; EMG; Inertial Sensors; Wearables; Wearable computing; Feature Selection; Big Data}, doi = {10.26092/elib/1219}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/Liu2021Diss.pdf} } @inproceedings{liu2022pipeline, title = {A Practical Wearable Sensor-Based Human Activity Recognition Research Pipeline}, author = {Liu, Hui and Hartmann, Yale and Schultz, Tanja}, booktitle = {Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2022) - Volume 5: HEALTHINF: WHC}, pages = {847--856}, organization = {INSTICC}, publisher = {SCITEPRESS - Science and Technology Publications}, year = {2022}, isbn = {978-989-758-552-4}, issn = {2184-4305}, doi = {10.5220/0010937000003123}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/LiuHartmannSchultz_Healthinf2022.pdf}, abstract = {Many researchers devote themselves to studying various aspects of Human Activity Recognition (HAR), such as data analysis, signal processing, feature extraction, and machine learning models. In response to the fact that few documents summarize and form intuitive paradigms for the entire HAR research pipeline, based on the purpose of sharing our years of research experience, we propose a practical, comprehensive HAR research pipeline, called HAR-Pipeline, composed of nine research aspects, aiming to reflect the overall perspective of HAR research topics to the greatest extent and indicate the sequence and relationship between the tasks. Supplemented by the outcomes of our actual series of studies as examples, we demonstrate the proposed pipeline's rationality and feasibility.} } @inproceedings{xue2021hmm, title = {Hidden {Markov} Model and Its Application in Human Activity Recognition and Fall Detection: {A} Review}, author = {Xue, Tingting and Liu, Hui}, booktitle = {Communications, Signal Processing, and Systems}, editor = {Liang, Qilian and Wang, Wei and Liu, Xin and Na, Zhenyu and Zhang, Baoju}, year = {2022}, publisher = {Springer Singapore}, pages = {863--869}, isbn = {978-981-19-0390-8}, doi = {10.1007/978-981-19-0390-8_108}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/XueLiu_Springer2022.pdf}, abstract= {This paper firstly describes the research framework of Human Activity Recognition and Fall Detection, as well as Hidden Markov Model and its extension with continuous observations and hierarchical topology, namely the Continuous Density Hidden Markov Model and the Hierarchical Hidden Markov Model. Subsequently, we introduce how to apply Hidden Markov Models to the human activity modeling in Human Activity Recognition and Fall Detection based on previous literature. Finally, famous research work for smart home technology and elderly care based on Hidden Markov Models is reviewed.} } @inproceedings{liu2011capacity, title = {Capacity of Cooperative Ad Hoc Networks with Heterogeneous Traffic Patterns}, author = {Liu, Hui and Wang, Xinbing}, booktitle = {2011 IEEE International Conference on Communications (ICC)}, pages = {1--5}, year = {2011}, organization = {IEEE} doi = {10.1109/icc.2011.5963075}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/LiuWang_ICC2011.pdf}, abstract= {We study the capacity of ad hoc network with heterogenous traffic patterns, specifically on the fields of multicast and unicast traffic. We apply hierarchical cooperation scheme, MIMO technology and multihop transmission mechanisms in both traffic patterns. The major contribution of this paper is a new capacity analysis method and procedure for the network with heterogenous traffic patterns. We use the index "Unicast capacity / Multicast capacity" to decide the capacitydominant traffic pattern, analyze the traffic parameters and derive the network capacity scaling in case of both hierarchical layers h(M) → ∞ and h(U) → ∞. Less-than-half multicast nodes would dominate the whole network capacity. Two indices 1−log n(2) and log n (n − 1) of the multicast scale m are very important in deciding the dominant traffic pattern for the network capacity, because when 0 ≤ m ≤ 1−log n(2) or log n (n − 1) ≤ m < 1, the aggregate network capacity is irrelated to the multicast destination scale d.} } @inproceedings{liu2022activity_duration, title = {How Long Are Various Types of Daily Activities? {Statistical} Analysis of a Multimodal Wearable Sensor-Based Human Activity Dataset}, author = {Liu, Hui and Schultz, Tanja}, booktitle = {Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2022) - Volume 5: HEALTHINF}, pages = {680--688}, organization = {INSTICC}, publisher = {SCITEPRESS - Science and Technology Publications}, year = {2022}, isbn = {978-989-758-552-4}, issn = {2184-4305}, doi = {10.5220/0010896400003123}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/LiuSchultz_Healthinf2022.pdf}, abstract = {Human activity research in the field of informatics, such as activity segmentation, modeling, and recognition, is moving in an increasingly interpretable direction with the introduction of sports and kinematics knowledge. Many related research topics face a question: How long is the typical duration of the activities needed to be modeled? Several public human activity datasets do not strictly limit single motions' repetition times, such as gait cycle numbers, in recording sessions, so they are not statistically significant concerning activity duration. Standing on the rigorous acquisition protocol design and well-segmented data corpus of the recently released multimodal wearable sensor-based human activity dataset CSL-SHARE, this paper analyzes the duration statistics and distribution of 22 basic single motions of daily activities and sports, hoping to provide research references for human activity studies. We discovered that (1) the duration of each studied human daily activity or simple sports activity reflects interpersonal similarities and naturally obeys a normal distribution; (2) one single motion (such as jumping and sitting down) or one cycle in the activities of cyclical motions (such as one gait cycle in walking) has an average duration in the interval from about 1 second to 2 seconds.} } @inproceedings{hartmann2022har_high_level_features, //note = {Best Student Paper Nomination: Finalist}, title = {Interpretable High-Level Features for Human Activity Recognition}, author = {Hartmann, Yale and Liu, Hui and Lahrberg, Steffen and Schultz, Tanja}, booktitle = {Proceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2022) - Volume 4: BIOSIGNALS}, pages = {40--49}, organization = {INSTICC}, publisher = {SCITEPRESS - Science and Technology Publications}, year = {2022}, isbn = {978-989-758-552-4}, issn = {2184-4305}, doi = {10.5220/0010840500003123}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/HartmannLiuLahrbergSchultz_Biosignals2022.pdf}, abstract = {This paper introduces and evaluates a novel way of processing human activities based on unique combinations of interpretable categorical high-level features with applications to classification, few-shot learning, as well as cross-dataset and cross-sensor comparison, combination, and analysis. Feature extraction is considered as a classification problem and solved with Hidden Markov Models making the feature space easily extensible. The feature extraction is person-independently evaluated on the CSL-SHARE and UniMiB SHAR datasets and achieves balanced accuracies up from 96.1% on CSL-SHARE and up to 91.1% on UniMiB SHAR. Furthermore, classification experiments on the separate and combined datasets achieve 85% (CSL-SHARE), 65% (UniMiB SHAR), and 74% (combined) accuracy. The few-shot learning experiments show potential with low errors in feature extraction but require further work for good activity classification. Remarkable is the possibility to attribute errors and indicate optimization areas easily. These experiments demonstrate the potential and possibilities of the proposed method and the high-level, extensible, and interpretable feature space.} } @article{schultz2021care, title={I-care-an interaction system for the individual activation of people with dementia}, author={Schultz, Tanja and Putze, Felix and Steinert, Lars and Mikut, Ralf and Depner, Anamaria and Kruse, Andreas and Franz, Ingo and Gaerte, Philipp and Dimitrov, Todor and Gehrig, Tobias and others}, journal={Geriatrics}, volume={6}, number={2}, pages={51}, year={2021}, publisher={Multidisciplinary Digital Publishing Institute} } @inproceedings{putze2021multimodal, title={Multimodal differentiation of obstacles in repeated adaptive human-computer interactions}, author={Putze, Felix and Salous, Mazen}, booktitle={26th International Conference on Intelligent User Interfaces}, pages={260--269}, year={2021} } @article{annerer2021reliably, title={How Reliably Do Eye Parameters Indicate Internal Versus External Attentional Focus?}, author={Annerer-Walcher, Sonja and Ceh, Simon M and Putze, Felix and Kampen, Marvin and K{\"o}rner, Christof and Benedek, Mathias}, journal={Cognitive Science}, volume={45}, number={4}, pages={e12977}, year={2021}, publisher={Wiley Online Library} } @article{solovey2021improving, title={Improving HCI with Brain Input: Review, Trends, and Outlook}, author={Solovey, Erin T and Putze, Felix}, journal={Foundations and Trends{\textregistered} in Human--Computer Interaction}, volume={13}, number={4}, year={2021} } @article{alharbi2020effects, title={The effects of predictive features of mobile keyboards on text entry speed and errors}, author={Alharbi, Ohoud and Stuerzlinger, Wolfgang and Putze, Felix}, journal={Proceedings of the ACM on Human-Computer Interaction}, volume={4}, number={ISS}, pages={1--16}, year={2020}, publisher={ACM New York, NY, USA} } @inproceedings{putze2020model, title={Model-Based Prediction of Exogeneous and Endogeneous Attention Shifts During an Everyday Activity}, author={Putze, Felix and Burri, Merlin and Vortmann, Lisa-Marie and Schultz, Tanja}, booktitle={Companion Publication of the 2020 International Conference on Multimodal Interaction}, pages={417--425}, year={2020} } @article{kuster_pdstd_2021, title = {PDSTD - The Portsmouth Dynamic Spontaneous Tears Database}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/Küster2021_Article_PDSTD-ThePortsmouthDynamicSpon.pdf}, issn = {1554-3528}, url = {https://doi.org/10.3758/s13428-021-01752-w}, doi = {10.3758/s13428-021-01752-w}, abstract = {The vast majority of research on human emotional tears has relied on posed and static stimulus materials. In this paper, we introduce the Portsmouth Dynamic Spontaneous Tears Database ({PDSTD}), a free resource comprising video recordings of 24 female encoders depicting a balanced representation of sadness stimuli with and without tears. Encoders watched a neutral film and a self-selected sad film and reported their emotional experience for 9 emotions. Extending this initial validation, we obtained norming data from an independent sample of naïve observers (N = 91, 45 females) who watched videos of the encoders during three time phases (neutral, pre-sadness, sadness), yielding a total of 72 validated recordings. Observers rated the expressions during each phase on 7 discrete emotions, negative and positive valence, arousal, and genuineness. All data were analyzed by means of general linear mixed modelling ({GLMM}) to account for sources of random variance. Our results confirm the successful elicitation of sadness, and demonstrate the presence of a tear effect, i.e., a substantial increase in perceived sadness for spontaneous dynamic weeping. To our knowledge, the {PDSTD} is the first database of spontaneously elicited dynamic tears and sadness that is openly available to researchers. The stimuli can be accessed free of charge via {OSF} from https://osf.io/uyjeg/?view\_only=24474ec8d75949ccb9a8243651db0abf.}, journal= {Behavior Research Methods}, shortjournal = {Behavior Research Methods}, author = {Küster, Dennis and Baker, Marc and Krumhuber, Eva G.}, year = {2021}, } @inbook{10.1145/3462244.3480978, author = {K\"{u}ster, Dennis and Putze, Felix and St-Onge, David and Fortin, Pascal E. and Urrestilla, Nerea and Schultz, Tanja}, title = {3rd Workshop on Modeling Socio-Emotional and Cognitive Processes from Multimodal Data in the Wild}, year = {2021}, isbn = {9781450384810}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3462244.3480978}, abstract = { Modeling with multimodal data in the wild poses similar challenges in human-computer and human-robot interaction (HCI, HRI). This workshop series thus blends HCI and HRI to jointly address a broad range of current topics in multimodal modeling aimed at designing intelligent systems in the wild. From addressing data scarcity in multimodal user state recognition to emotion prediction from EEG while listening to music, our third workshop in this series aims to further stimulate this important multidisciplinary exchange.}, booktitle = {Proceedings of the 2021 International Conference on Multimodal Interaction}, pages = {860–861}, numpages = {2} } @article{krumhuber_human_2021, title = {Human and machine validation of 14 databases of dynamic facial expressions}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/Krumhuber_et_al_2020_Human_and_machine_validation_of_14_databases_of_dynamic_facial_expressions.pdf}, volume = {53}, issn = {1554-3528}, doi = {10.3758/s13428-020-01443-y}, abstract = {With a shift in interest toward dynamic expressions, numerous corpora of dynamic facial stimuli have been developed over the past two decades. The present research aimed to test existing sets of dynamic facial expressions (published between 2000 and 2015) in a cross-corpus validation effort. For this, 14 dynamic databases were selected that featured facial expressions of the basic six emotions (anger, disgust, fear, happiness, sadness, surprise) in posed or spontaneous form. In Study 1, a subset of stimuli from each database (N = 162) were presented to human observers and machine analysis, yielding considerable variance in emotion recognition performance across the databases. Classification accuracy further varied with perceived intensity and naturalness of the displays, with posed expressions being judged more accurately and as intense, but less natural compared to spontaneous ones. Study 2 aimed for a full validation of the 14 databases by subjecting the entire stimulus set (N = 3812) to machine analysis. A {FACS}-based Action Unit ({AU}) analysis revealed that facial {AU} configurations were more prototypical in posed than spontaneous expressions. The prototypicality of an expression in turn predicted emotion classification accuracy, with higher performance observed for more prototypical facial behavior. Furthermore, technical features of each database (i.e., duration, face box size, head rotation, and motion) had a significant impact on recognition accuracy. Together, the findings suggest that existing databases vary in their ability to signal specific emotions, thereby facing a trade-off between realism and ecological validity on the one end, and expression uniformity and comparability on the other.}, pages = {686--701}, number = {2}, journal= {Behavior Research Methods}, shortjournal = {Behavior Research Methods}, author = {Krumhuber, Eva G. and Küster, Dennis and Namba, Shushi and Skora, Lina}, year = {2021}, } @ARTICLE{10.3389/frobt.2022.836462, AUTHOR={Serholt, Sofia and Ekström, Sara and Küster, Dennis and Ljungblad, Sara and Pareto, Lena}, TITLE={Comparing a Robot Tutee to a Human Tutee in a Learning-By-Teaching Scenario with Children}, JOURNAL={Frontiers in Robotics and AI}, VOLUME={9}, YEAR={2022}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/Serholt_et_al._-_2022_-_Comparing_a_Robot_Tutee_to_a_Human_Tutee_in_a_Lear.pdf}, DOI={10.3389/frobt.2022.836462}, ISSN={2296-9144}, ABSTRACT={Social robots are increasingly being studied in educational roles, including as tutees in learning-by-teaching applications. To explore the benefits and drawbacks of using robots in this way, it is important to study how robot tutees compare to traditional learning-by-teaching situations. In this paper, we report the results of a within-subjects field experiment that compared a robot tutee to a human tutee in a Swedish primary school. Sixth-grade students participated in the study as tutors in a collaborative mathematics game where they were responsible for teaching a robot tutee as well as a third-grade student in two separate sessions. Their teacher was present to provide support and guidance for both sessions. Participants’ perceptions of the interactions were then gathered through a set of quantitative instruments measuring their enjoyment and willingness to interact with the tutees again, communication and collaboration with the tutees, their understanding of the task, sense of autonomy as tutors, and perceived learning gains for tutor and tutee. The results showed that the two scenarios were comparable with respect to enjoyment and willingness to play again, as well as perceptions of learning gains. However, significant differences were found for communication and collaboration, which participants considered easier with a human tutee. They also felt significantly less autonomous in their roles as tutors with the robot tutee as measured by their stated need for their teacher’s help. Participants further appeared to perceive the activity as somewhat clearer and working better when playing with the human tutee. These findings suggest that children can enjoy engaging in peer tutoring with a robot tutee. However, the interactive capabilities of robots will need to improve quite substantially before they can potentially engage in autonomous and unsupervised interactions with children.} } @inproceedings{hartmann2022demo, title = {Interactive and Interpretable Online Human Activity Recognition}, author = {Hartmann, Yale and Liu, Hui and Schultz, Tanja}, booktitle = {PERCOM 2022 - 20th IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops)}, year = {2022}, pages = {109--111}, doi = {10.1109/PerComWorkshops53856.2022.9767207}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/HartmannLiuSchultz_PERCOM2022.pdf}, abstract = {This demo paper puts forward our interactive and inspectable real-time recognition demo for human activity recognition. The demo captures online data from wearable sensors such as inertial measurement units, recognizes the performed human activity using Hidden Markov Models, and displays the search's current state along with the recognition results in real-time. Therefore, allowing users to interact with the system and probe its recognition by altering their actions and comparing their expectations with the demo's performance. Students, Researchers, or the general public can easily extend the detected classes by utilizing the integrated recording, segmentation, and re-training tools — all while running on moderate hardware or even IoT devices like a Raspberry Pi. The demo is titled "ASK2.0" and provides an easy-to-use and powerful way to teach and explain real-time human activity recognition and machine learning.} } @article{folgado2022tssearch, title = {{TSSEARCH}: {Time} Series Subsequence Search Library}, author = {Folgado, Duarte and Barandas, Mar{\'\i}lia and Antunes, Margarida and Nunes, Maria Lua and Liu, Hui and Hartmann, Yale and Schultz, Tanja and Gamboa, Hugo}, journal = {SoftwareX}, volume = {18}, pages = {101049}, year = {2022}, issn = {2352-7110}, doi = {https://doi.org/10.1016/j.softx.2022.101049}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/TSSEARCH_SoftwareX2022.pdf}, abstract = {Subsequence Search and distance measures are crucial tools in time series data mining. This paper presents our Python package entitled TSSEARCH, which provides a comprehensive set of methods for subsequence search and similarity measurement in time series. These methods are user-customizable for more flexibility and efficient integration into real deployment scenarios. TSSEARCH enables fast exploratory time series data analysis and was validated in the context of Human Activity Recognition and Indoor Localization.} } @INPROCEEDINGS{ablimit2022crosscorpus, author={Ablimit, Ayimnisagul and Botelho, Catarina and Abad, Alberto and Schultz, Tanja and Trancoso, Isabel}, booktitle={ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, title={Exploring dementia detection from speech: cross corpus analysis}, year={2022}, volume={}, number={}, pages={6472-6476}, doi={10.1109/ICASSP43922.2022.9747167}, ISSN={}, month={May}, abstract={In this work, we present a qualitative and quantitative analysis of speech and language features derived from two different corpora with the aim to predict early signs of dementia. One corpus consists of the Interdisciplinary Longitudinal Study on Adult Development and Aging (ILSE) designed to investigate satisfying and healthy aging. It consists of more than 6500 hours of biographic interviews from 1000 participants recorded over the course of 20 years. The other corpus is a cross sectional data set created for the ADReSS challenge 2020. In an experimental study we describe a large variety of acoustic and linguistic features that are automatically extracted from speech and corresponding transcriptions. We compare different traditional classifiers, i.e. Gaussian Mixture Models, Linear Discriminant Analysis, and Support Vector Machines. Our final performance results surpass the ADReSS benchmarks.}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/ablimit_ICASP2022.pdf} } @inproceedings{borsdorf2022ExpertsVersusAllrounders, title={Experts Versus All-rounders: Target Language Extraction for Multiple Target Languages}, author={Borsdorf, Marvin and Scheck, Kevin and Li, Haizhou and Schultz, Tanja}, booktitle={2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, year={2022}, pages={846--850}, doi={10.1109/ICASSP43922.2022.9746130}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Borsdorf2022ExpertsVersusAllrounders.pdf}, abstract={Target language extraction (TLE) is a novel task in the field of selective auditory attention, which seeks to extract all speech signals that are spoken in a target language from other sources in a multilingual cocktail party. In our prior studies, a TLE model was trained to extract a predefined, single target language, referred to as Single-TLE. In this paper, we extend the Single-TLE framework to Multi-TLE. Multi-TLE models can also extract all speech signals of one specific target language, but they are optimized on a set of multiple target languages during training. As such, they learn the characteristics of several target languages and can replace multiple Single-TLE models without retraining. We perform experiments on the GlobalPhoneMCP database and incorporate a dynamic language mixing scheme for training. The Multi-TLE model does not only outperform Single-TLE models, but when given a language ID as additional input, it is also able to extract the speech of a specific target language from a mixture which contains multiple learned target languages.} } @INPROCEEDINGS{angrick2022ClosedLoopUnitSelection, author={Angrick, Miguel and Ottenhoff, Maarten and Diener, Lorenz and Ivucic, Darius and Ivucic, Gabriel and Goulis, Sophocles and Colon, Albert J. and Wagner, Louis and Krusienski, Dean J. and Kubben, Pieter L. and Schultz, Tanja and Herff, Christian}, booktitle={ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, title={Towards Closed-Loop Speech Synthesis from Stereotactic EEG: A Unit Selection Approach}, year={2022}, volume={}, number={}, pages={1296-1300}, abstract={Neurological disorders can severely impact speech communication. Recently, neural speech prostheses have been proposed that reconstruct intelligible speech from neural signals recorded superficially on the cortex. Thus far, it has been unclear whether similar reconstruction is feasible from deeper brain structures, and whether audible speech can be directly synthesized from these reconstructions with low-latency, as required for a practical speech neuroprosthetic. The present study aims to address both challenges. First, we implement a low-latency unit selection based synthesizer that converts neural signals into audible speech. Second, we evaluate our approach on open-loop recordings from 5 patients implanted with stereotactic depth electrodes who conducted a read-aloud task of Dutch utterances. We achieve correlation coefficients significantly higher than chance level of up to 0.6 and an average computational cost of 6.6 ms for each 10 ms frames. While the current reconstructed utterances are not intelligible, our results indicate promising decoding and run-time capabilities that are suitable for investigations of speech processes in closed-loop experiments.}, keywords={}, doi={10.1109/ICASSP43922.2022.9747300}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Angrick_ICASP22.pdf}, ISSN={2379-190X}, month={May},} @Article{s22093533, AUTHOR = {Huang, Jiahui and Chia, Yew Ken and Yu, Samson and Yee, Kevin and Küster, Dennis and Krumhuber, Eva G. and Herremans, Dorien and Roig, Gemma}, TITLE = {Single Image Video Prediction with Auto-Regressive GANs}, JOURNAL = {Sensors}, VOLUME = {22}, YEAR = {2022}, NUMBER = {9}, ARTICLE-NUMBER = {3533}, URL = {https://www.mdpi.com/1424-8220/22/9/3533}, ISSN = {1424-8220}, ABSTRACT = {In this paper, we introduce an approach for future frames prediction based on a single input image. Our method is able to generate an entire video sequence based on the information contained in the input frame. We adopt an autoregressive approach in our generation process, i.e., the output from each time step is fed as the input to the next step. Unlike other video prediction methods that use “one shot” generation, our method is able to preserve much more details from the input image, while also capturing the critical pixel-level changes between the frames. We overcome the problem of generation quality degradation by introducing a “complementary mask” module in our architecture, and we show that this allows the model to only focus on the generation of the pixels that need to be changed, and to reuse those that should remain static from its previous frame. We empirically validate our methods against various video prediction models on the UT Dallas Dataset, and show that our approach is able to generate high quality realistic video sequences from one static input image. In addition, we also validate the robustness of our method by testing a pre-trained model on the unseen ADFES facial expression dataset. We also provide qualitative results of our model tested on a human action dataset: The Weizmann Action database.}, DOI = {10.3390/s22093533} } @article{putze2022understanding, title={Understanding HCI Practices and Challenges of Experiment Reporting with Brain Signals: Towards Reproducibility and Reuse}, author={Putze, Felix and Putze, Susanne and Sagehorn, Merle and Micek, Christopher and Solovey, Erin T}, journal={ACM Transactions on Computer-Human Interaction (TOCHI)}, volume={29}, number={4}, pages={1--43}, year={2022}, publisher={ACM New York, NY} } @inproceedings{vortmann2022differentiating, title={Differentiating Endogenous and Exogenous Attention Shifts Based on Fixation-Related Potentials}, author={Vortmann, Lisa-Marie and Schult, Moritz and Putze, Felix}, booktitle={27th International Conference on Intelligent User Interfaces}, pages={243--257}, year={2022} } @article{vortmann2022multimodal, title={Multimodal EEG and Eye Tracking Feature Fusion Approaches for Attention Classification in Hybrid BCIs}, author={Vortmann, Lisa-Marie and Ceh, Simon and Putze, Felix}, journal={Frontiers in Computer Science}, volume={4}, pages={780580}, year={2022}, publisher={Frontiers Media SA} } @inproceedings{vortmann2021ssvep, title={SSVEP-Aided Recognition of Internally and Externally Directed Attention from Brain Activity}, author={Vortmann, Lisa-Marie and Klaff, Jonas and Urban, Timo and Putze, Felix}, booktitle={2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)}, pages={2672--2677}, year={2021}, organization={IEEE} } @article{vortmann2021exploration, title={Exploration of Person-Independent BCIs for Internal and External Attention-Detection in Augmented Reality}, author={Vortmann, Lisa-Marie and Putze, Felix}, journal={Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies}, volume={5}, number={2}, pages={1--27}, year={2021}, publisher={ACM New York, NY, USA} } @article{vortmann2021using, title={Using Brain Activity Patterns to Differentiate Real and Virtual Attended Targets during Augmented Reality Scenarios}, author={Vortmann, Lisa-Marie and Schwenke, Leonid and Putze, Felix}, journal={Information}, volume={12}, number={6}, pages={226}, year={2021}, publisher={Multidisciplinary Digital Publishing Institute} } @article{vortmann2021imaging, title={Imaging Time Series of Eye Tracking Data to Classify Attentional States}, author={Vortmann, Lisa-Marie and Knychalla, Jannes and Annerer-Walcher, Sonja and Benedek, Mathias and Putze, Felix}, journal={Frontiers in Neuroscience}, volume={15}, pages={625}, year={2021}, publisher={Frontiers} } @inproceedings{putze2023analyzing, title={Analyzing the Importance of EEG Channels for Internal and External Attention Detection}, author={Putze, Felix and Eilts, Hendrik}, booktitle={2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)}, pages={4752--4757}, year={2023}, organization={IEEE} } @inproceedings{pahuja2023enhancing, title={Enhancing Subject-Independent EEG-Based Auditory Attention Decoding with WGAN and Pearson Correlation Coefficient}, author={Pahuja, Saurav and Ivucic, Gabriel and Putze, Felix and Cai, Siqi and Li, Haizhou and Schultz, Tanja}, booktitle={2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)}, pages={3715--3720}, year={2023}, organization={IEEE} } @inproceedings{vortmann2023machine, title={Machine Learning from Mistakes: Self-Improving Attention Classifier Using Error-Related Potentials}, author={Vortmann, Lisa-Marie and Urban, Timo and Putze, Felix}, booktitle={2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)}, pages={4770--4777}, year={2023}, organization={IEEE} } @article{ceh2023di, title={DI-WHAT? Identifying creative domains in do-it-yourself videos on YouTube.}, author={Ceh, Simon and Putze, Felix and Benedek, Mathias}, journal={Psychology of Aesthetics, Creativity, and the Arts}, year={2023}, publisher={Educational Publishing Foundation} } @article{jahanian2023tool, title={Tool-use training in augmented reality: Plasticity of forearm body schema does not predict sense of ownership or agency in older adults}, author={Jahanian Najafabadi, Amir and K{\"u}ster, Dennis and Putze, Felix and Godde, Ben}, journal={Experimental Brain Research}, volume={241}, number={7}, pages={1739--1756}, year={2023}, publisher={Springer} } @article{najafabadi2023emergence, title={Emergence of sense of body ownership but not agency during virtual tool-use training is associated with an altered body schema}, author={Najafabadi, Amir Jahanian and K{\"u}ster, Dennis and Putze, Felix and Godde, Ben}, journal={Experimental Brain Research}, volume={241}, number={7}, pages={1721--1738}, year={2023}, publisher={Springer} } @article{richter2023eeg, title={Eeg correlates of distractions and hesitations in human--robot interaction: a lablinking pilot study}, author={Richter, Birte and Putze, Felix and Ivucic, Gabriel and Brandt, Mara and Sch{\"u}tze, Christian and Reisenhofer, Rafael and Wrede, Britta and Schultz, Tanja}, journal={Multimodal Technologies and Interaction}, volume={7}, number={4}, pages={37}, year={2023}, publisher={MDPI} } @inproceedings{liu2022pitch_histogram, //note = {Best Paper Award Nomination: Finalist}, title = {Merged Pitch Histograms and Pitch-Duration Histograms}, author = {Liu, Hui and Xue, Tingting and Schultz, Tanja}, booktitle = {Proceedings of the 19th International Conference on Signal Processing and Multimedia Applications (SIGMAP 2022)}, pages = {32-39}, organization = {INSTICC}, publisher = {SCITEPRESS - Science and Technology Publications}, year = {2022}, doi = {10.5220/0011310300003289}, isbn = {978-989-758-591-3}, issn = {2184-9471}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/LiuXueSchultz_SIGMAP2022.pdf}, abstract = {The traditional pitch histogram and various features extracted from it play a pivotal role in music information retrieval. In the research on songs, especially applying pitch statistics to investigate the main melody, we found that the pitch histogram may not necessarily reflect the notes' pitch characteristic of the whole song perfectly. Therefore, we took the note duration into account to propose two advanced versions of pitch histograms and validated their applicability. This paper introduces these two novel histograms: the merged pitch histogram by merging consecutively repeated pitches and the pitch-duration histogram by utilizing each pitch's duration information. Complemented by the description of their calculation algorithms, the discussion of their advantages and limitations, the analysis of their application to songs from various languages and cultures, and the demonstration of their use cases in state-of-the-art research works, the proposed histograms' characteristics and usefulness are intuitively revealed.} } @article{liu2022pentatonic_bell_shape, author = {Liu, Hui and Jiang, Kun and Gamboa, Hugo and Xue, Tingting and Schultz, Tanja}, title = {Bell Shape Embodying Zhongyong: {The} Pitch Histogram of Traditional Chinese Anhemitonic Pentatonic Folk Songs}, journal = {Applied Sciences}, volume = {12}, year = {2022}, number = {16}, article-number = {8343}, issn = {2076-3417}, doi = {10.3390/app12168343}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/LiuJiangGamboaXueSchultz_Applied_Sciences_2022.pdf}, abstract = {As an essential subset of Chinese music, traditional Chinese folk songs frequently apply the anhemitonic pentatonic scale. In music education and demonstration, the Chinese anhemitonic pentatonic mode is usually introduced theoretically, supplemented by music appreciation, and a non-Chinese-speaking audience often lacks a perceptual understanding. We discovered that traditional Chinese anhemitonic pentatonic folk songs could be identified intuitively according to their distinctive bell-shaped pitch distribution in different types of pitch histograms, reflecting the Chinese characteristics of Zhongyong (the doctrine of the mean). Applying pitch distribution to the demonstration of the Chinese anhemitonic pentatonic folk songs, exemplified by a considerable number of instances, allows the audience to understand the culture behind the music from a new perspective by creating an auditory and visual association. We have also made preliminary attempts to feature and model the observations and implemented pilot classifiers to provide references for machine learning in music information retrieval (MIR). To the best of our knowledge, this article is the first MIR study to use various pitch histograms on traditional Chinese anhemitonic pentatonic folk songs, demonstrating that, based on cultural understanding, lightweight statistical approaches can progress cultural diversity in music education, computational musicology, and MIR.} } @inproceedings{borsdorf2022BlindLanguageSeparation, title={{Blind Language Separation: Disentangling Multilingual Cocktail Party Voices by Language}}, author={Borsdorf, Marvin and Scheck, Kevin and Li, Haizhou and Schultz, Tanja}, booktitle={{Proceedings of the 23rd Annual Conference of the International Speech Communication Association (INTERSPEECH)}}, year={2022}, pages={256--260}, doi={10.21437/Interspeech.2022-10187}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Borsdorf2022BlindLanguageSeparation.pdf}, abstract={We introduce blind language separation (BLS) as novel research task, in which we seek to disentangle overlapping voices of multiple languages by language. BLS is expected to separate seen as well as unseen languages, which is different from the target language extraction task that works for one seen target language at a time. To develop a BLS model, we simulate a multilingual cocktail party database, of which each scene consists of two randomly selected languages, each represented by two randomly selected speakers. The database follows the recently proposed GlobalPhoneMCP database design concept that uses the audio data of the GlobalPhone 2000 Speaker Package. We show that a BLS model is able to learn the language characteristics so as to disentangle overlapping voices by language. We achieve a mean SI-SDR improvement of 12.63 dB over 231 test sets. The performance on the individual test sets varies depending on the language combination. Finally, we show that BLS can generalize well to unseen speakers and languages in the mixture.}, } @inproceedings{ablimit2022StateScreening, title={{Deep Learning Approaches for Detecting Alzheimer's Dementia from Conversational Speech of ILSE Study}}, author={Ablimit, Ayimnisagul and Scholz, Karen and Schultz, Tanja}, booktitle={{Proceedings of the 23rd Annual Conference of the International Speech Communication Association (INTERSPEECH)}}, year={2022}, pages={xx}, doi={xx}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ablimit2022StateScreening.pdf}, abstract={Automatic screening of Alzheimer's Dementia (AD) can have significant impact on society and the well-being of the patients. Early detection of AD from spontaneous speech offers great potential for inexpensive and convenient casual testing. We propose our deep neural network architecture that leverages acoustic, linguistic and demographic features to build a model for dementia screening for the biographic interview speech corpus of Interdisciplinary Longitudinal Study on Adult Development and Aging (ILSE). We oversample non-sequential and sequential features using well-known oversampling techniques and adapted data augmentation techniques to overcome the challenge of the imbalanced dataset, since the distribution of the diagnostic groups in ILSE corresponds to the prevalence of dementia. Our system achieves 70.6% of unweighted average recall on a 3-class classification problem. Moreover, we also investigate the feature importances to the model prediction to identify the most relevant indicators for AD detection, which may contribute to interpreting signs of cognitive decline and thus supporting clinicians in the diagnosis of dementia.}, } @inproceedings{salous2022smarthelm, title={SmartHelm: User Studies from Lab to Field for Attention Modeling}, author={Salous, Mazen and K\"{u}ster, Dennis and Scheck, Kevin and Dikfidan, Aytac and Neumann, Tim and Putze, Felix and Schultz, Tanja}, booktitle={2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC)}, pages={xx}, year={2022}, organization={IEEE}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/salous2022smarthelm.pdf}, abstract={We present three user studies that gradually prepare our prototype system SmartHelm for use in the field, i.e. supporting cargo cyclists on public roads for cargo delivery. SmartHelm is an attention-sensitive smart helmet that integrates none-invasive brain and eye activity detection with hands-free Augmented Reality (AR) components in a speech-enabled outdoor assistance system. The described studies systematically increased in ecological validity from lab to field. The first study consisted of an Augmented Reality preparation examination in the lab. The second study then investigated simulated attention distraction modeling, whereas the third study examined real world attention distraction modeling while cycling in traffic. During these three studies, multimodal data (EEG, eye-tracking, video, GPS and speech) has been collected synchronously and analyzed in offline and online experiments. Machine Learning models were trained and optimized for attention modeling. Results: Analyses of self-report and objective data during the simulation study show the plausibility of the simulated internal and external distractions. The analysis of behavioral data captured by multimodal biosignals recorded in the field study further shows that real visual attention distractions can be automatically identified using synchronized video and eye tracking data. Machine Learning methods based on long short term memory models (LSTMs) indicate that simulated attention distractions can be automatically detected from EEG data, with the best detection performance for mental distractions. Finally, the self-report data suggest that the comfort of the SmartHelm helmet should be further improved for permanent use in road traffic.} } @inproceedings{boudjema2023lightcnn, title = {A Light CNN Architecture for Human Activity Recognition Based Wearable Sensors}, author = {Boudjema, Ali and Faiza, Titouna and Hattab, Abdessalam and Djouzi, Kheyreddine}, year = {2023}, month = {05}, booktitle = {First National Conference in Computer Science Research and its Applications}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Boudjema2023.pdf}, abstract = {With the evolution of sensors technology, a variety of real-life applications, including healthcare, industrial monitoring, and cyber-security, exploited its strengths like the low cost and the small size. Collected data from sensors create a special pattern known by time series. Data collected via sensors in order to recognize human activities form a time series classification problem known as human activity recognition (HAR). The multimodality and high dimensionality of the obtained readings make identifying complicated human activity harder. To address these problems, we suggest a light deep learning-based model for human activity recognition. We evaluated our proposed Convolutional Neural Network model's performance on complex human activities collected from wearable sensors using two public datasets, WISDM and PAMAP2. Additionally, we compared our model's performance to several DL models and existing HAR systems to demonstrate its effectiveness. The results show that our model outperforms the compared methods across a variety of metrics by reaching an accuracy of 94.31% and 99.71% using 30k and 25k parameters on PAMAP2 and WISDM datasets, respectively.} } @article{rodriguesliu2022ssm_novelty, title= {Feature-Based Information Retrieval of Multimodal Biosignals with a Self-Similarity Matrix: {Focus} on Automatic Segmentation}, author = {{Rodrigues, João and Liu, Hui} and Folgado, Duarte and Belo, David and Schultz, Tanja and Gamboa, Hugo}, journal = {Biosensors}, volume = {12}, year = {2022}, number = {12}, article-number = {1182}, issn = {2079-6374}, doi = {10.3390/bios12121182}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/RodriguesLiuFolgadoBeloSchultzGamboa_Biosensors_2022.pdf}, abstract = {Biosignal-based technology has been increasingly available in our daily life, being a critical information source. Wearable biosensors have been widely applied in, among others, biometrics, sports, health care, rehabilitation assistance, and edutainment. Continuous data collection from biodevices provides a valuable volume of information, which needs to be curated and prepared before serving machine learning applications. One of the universal preparation steps is data segmentation and labelling/annotation. This work proposes a practical and manageable way to automatically segment and label single-channel or multimodal biosignal data using a self-similarity matrix (SSM) computed with signals' feature-based representation. Applied to public biosignal datasets and a benchmark for change point detection, the proposed approach delivered lucid visual support in interpreting the biosignals with the SSM while performing accurate automatic segmentation of biosignals with the help of the novelty function and associating the segments grounded on their similarity measures with the similarity profiles. The proposed method performed superior to other algorithms in most cases of a series of automatic biosignal segmentation tasks; of equal appeal is that it provides an intuitive visualization for information retrieval of multimodal biosignals.} } @article{liu2023sensors_har_editorial, title = {Sensor-Based Human Activity and Behavior Research: {Where} Advanced Sensing and Recognition Technologies Meet}, author = {Liu, Hui and Gamboa, Hugo and Schultz, Tanja}, journal = {Sensors}, volume = {23}, year = {2023}, number = {1}, article-number = {125}, issn = {1424-8220}, doi = {10.3390/s23010125}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/LiuGamboaSchultz_Editorial_Sensors2023.pdf} } @inproceedings{liu2023realtime_har, title = {On a Real Real-Time Wearable Human Activity Recognition System}, author = {Liu, Hui and Xue, Tingting and Schultz, Tanja}, booktitle = {Proceedings of the 16th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2023) - Volume 5: HEALTHINF: WHC}, pages = {711--720}, organization = {INSTICC}, publisher = {SCITEPRESS - Science and Technology Publications}, year = {2023}, isbn = {978-989-758-631-6}, issn = {2184-4305}, doi = {10.5220/0011927700003414}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/LiuXueSchultz_WHC2023.pdf}, abstract = {Many human activity recognition (HAR) systems have the ultimate application scenarios in real-time, while most literature has limited the HAR study to offline models. Some mentioned real-time or online applications, but the investigation of implementing and evaluating a real-time HAR system was missing. With our years of experience developing and demonstrating real-time HAR systems, we brief the implementation of offline HAR models, including hardware specifications, software engineering, data collection, biosignal processing, feature study, and human activity modeling, and then focus on the transition from offline to real-time models for details of window length, overlap ratio, sensor/device selection, feature selection, graphical user interface (GUI), and on-the-air functionality. We also indicate the evaluation of a real-time HAR system and put forward tips to improve the performance of wearable-based HAR.} } @INPROCEEDINGS{Scheck2023SUE2S, author={Scheck, Kevin and Schultz, Tanja}, booktitle={ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, title={Multi-speaker Speech Synthesis from Electromyographic Signals by Soft Speech Unit Prediction}, year={2023}, volume={}, number={}, pages={1-5}, doi={10.1109/ICASSP49357.2023.10097120}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ScheckSchultz-ICASSP23.pdf}, abstract={Electromyographic (EMG) signals of articulatory muscles reflect the speech production process even if the user is speaking silently i.e. moving the articulators without producing audible sound. We propose Speech-Unit-based EMG-to-Speech (SU-E2S), a system which relies on EMG to synthesize speech which contains the articulated content but is vocalized in another voice, determined by an acoustic reference utterance. It is based on a Voice Conversion (VC) system which decomposes acoustic speech into continuous soft speech units and a speaker embedding and then reconstructs acoustic features. SU-E2S performs speech synthesis by predicting soft speech units from EMG and using them as input to the VC system. Experiments show that the SU-E2S output is on par in terms of intelligibility of predicting acoustic features directly from EMG, but adds the functionality of synthesizing speech in other voices.} } @INPROCEEDINGS{Scheck24EMBC, author={Scheck, Kevin and Ren, Zhao and Dombeck, Tom and Sonnert, Jenny and van Gogh, Stefano and Hou, Qinhan and Wand, Michael and Schultz, Tanja}, title={{Cross-Speaker Training and Adaptation for Electromyography-to-Speech Conversion}}, booktitle={2024 46th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)}, year={2024}, volume={}, number={}, pages={1-4}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Scheck-EMBC24.pdf}, abstract={Surface Electromyography (EMG) signals of articulatory muscles can be used to synthesize acoustic speech with Electromyography-to-Speech (ETS) models. Recent models have improved the synthesis quality by combining training data from multiple recordings of single speakers. In this work, we evaluated whether using recordings of multiple speakers also increases performance and if cross-speaker models can be adapted to unseen speakers with limited data. We recorded the EMG-Vox corpus, which consists of EMG and audio signals of four speakers with five sessions each. We compared cross-speaker models with single-speaker counterparts and conducted adaptation experiments. Cross-speaker models achieved on average significantly better performance than single-speaker models. Experiments with balanced data indicated that this improvement stemmed from a larger training set. Performing speaker adaptation from cross-speaker models showed higher synthesis quality than training from scratch and was at least on par with session adaptation for most speakers. To the best of our knowledge, this is the first work to report that cross-speaker ETS models yielded better results than single-speaker models.} } @article{steinert2022predicting, title={Predicting activation liking of people with dementia}, author={Steinert, Lars and Putze, Felix and K{\"u}ster, Dennis and Schultz, Tanja}, journal={Frontiers in Computer Science}, volume={3}, pages={770492}, year={2022}, publisher={Frontiers Media SA}, url={https://www.frontiersin.org/articles/10.3389/fcomp.2021.770492/full} } @inproceedings{steinert2022evaluation, title={Evaluation of an engagement-aware recommender system for people with dementia}, author={Steinert, Lars and K{\"o}lling, Fynn Linus and Putze, Felix and K{\"u}ster, Dennis and Schultz, Tanja}, booktitle={Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization}, pages={89--98}, year={2022}, url={https://dl.acm.org/doi/10.1145/3503252.3531318} } @inproceedings{dudzik20224th, title={The 4th workshop on modeling socio-emotional and cognitive processes from multimodal data in-the-wild (MSECP-Wild)}, author={Dudzik, Bernd and K{\"u}ster, Dennis and St-Onge, David and Putze, Felix}, booktitle={Proceedings of the 2022 International Conference on Multimodal Interaction}, pages={803--804}, year={2022}, url={https://dl.acm.org/doi/10.1145/3536221.3564029} } @article{kuster2022teardrops, title={Teardrops on My Face: Automatic Weeping Detection from Nonverbal Behavior}, author={K{\"u}ster, Dennis and Steinert, Lars and Baker, Marc and Bhardwaj, Nikhil and Krumhuber, Eva G}, journal={IEEE Transactions on Affective Computing}, year={2022}, publisher={IEEE}, url={https://ieeexplore.ieee.org/abstract/document/9984983}, abstract={Human emotional tears are a powerful socio-emotional signal. Yet, they have received relatively little attention in empirical research compared to facial expressions or body posture. While humans are highly sensitive to others' tears, to date, no automatic means exist for detecting spontaneous weeping. This paper employed facial and postural features extracted using four pre-trained classifiers (FACET, Affdex, OpenFace, OpenPose) to train a Support Vector Machine (SVM) to distinguish spontaneous weepers from non-weepers. Results showed that weeping can be accurately inferred from nonverbal behavior. Importantly, this distinction can be made before the appearance of visible tears on the face. However, features from at least two classifiers need to be combined, with the best models blending three or four classifiers to achieve near-perfect performance (97% accuracy). We discuss how direct and indirect tear detection methods may help to yield important new insights into the antecedents and consequences of emotional tears and how affective computing could benefit from the ability to recognize and respond to this uniquely human signal.} } @article{najafabadi2022emergence, title={Emergence of sense of body ownership but not agency during virtual tool-use training is associated with an altered body schema}, author={Najafabadi, Amir Jahanian and K{\"u}ster, Dennis and Putze, Felix and Godde, Ben}, year={2022}, url={https://psyarxiv.com/8tf7w/} } @article{najafabadi2022tool, title={Tool-use training in augmented reality: Plasticity of forearm body schema does not predict sense of ownership or agency in older adults}, author={Najafabadi, Amir Jahanian and K{\"u}ster, Dennis and Putze, Felix and Godde, Ben}, year={2022}, url={https://psyarxiv.com/bvqma/} } @inproceedings{ivucic2022interpretable, title={Interpretable Deep Neural Networks for EEG-based Auditory Attention Detection with Layer-Wise Relevance Propagation}, author={Ivucic, Gabriel and Putze, Felix and Cai, Siqi and Li, Haizhou and Schultz, Tanja}, booktitle={The Third Neuroadaptive Technology Conference}, year={2022}, address={L{\"u}bbenau, Germany}, month={October 9--12}, pages={1--5}, url={https://neuroadaptive.org/wp-content/uploads/2022/10/NAT22_Programme.pdf}, abstract={Deep Neural Networks (DNNs) recently found their way into cognitive neuroscience serving as powerful computational models. However, the complexity of deep learning models results in an uninterpretable black box, preventing neurophysiological insight into processes behind the decision of the model. In this work, we present an explanation approach for a DNN in spatial auditory attention detection (AAD) with electroencephalography (EEG), based on Layer-Wise Relevance Propagation (LRP). LRP decomposes the prediction of the DNN into relevance heatmaps that represent the importance of the spectro-spatial image features regarding the decision of the network, illustrated in Figure 1. To validate the LRP explanation for the DNN, (1) the relation between relevance heatmaps and the output of the network is examined via relevance-guided input perturbation. Further, (2) structural features and potential prediction strategies in the LRP heatmaps are investigated by spectral clustering of relevance heatmaps. The results indicate that explanation heatmaps generated by LRP highlight areas in the cortical activation images that predominantly impact the decision of the network. The clustering approach found distinct patterns in relevance maps, individually for each subject, revealing the importance of neuro-physiologically plausible frontal, lateral, and rear brain areas for auditory attention. This work demonstrates that LRP can fill the interpretability gap in the development of DNNs for EEG- based AAD. The relevance heatmaps of single input samples combined with the knowledge of global prediction strategies open up the ability to investigate sample groups of interest at will, which renders LRP as a tool to reveal potential neural- or decisional processes underlying the deep learning model.} } @article{kuster2023kunstliche, title={K{\"u}nstliche Intelligenz und Ethik im Gesundheitswesen--Spagat oder Symbiose?}, author={K{\"u}ster, Dennis and Schultz, Tanja}, journal={Bundesgesundheitsblatt-Gesundheitsforschung-Gesundheitsschutz}, pages={1--8}, year={2023}, publisher={Springer}, url={https://link.springer.com/article/10.1007/s00103-022-03653-5}, abstract={Artificial intelligence (AI) is becoming increasingly important in healthcare. This development triggers serious concerns that can be summarized by six major “worst-case scenarios”. From AI spreading disinformation and propaganda, to a potential new arms race between major powers, to a possible rule of algorithms (“algocracy”) based on biased gatekeeper intelligence, the real dangers of an uncontrolled development of AI are by no means to be underestimated, especially in the health sector. However, fear of AI could cause humanity to miss the opportunity to positively shape the development of our society together with an AI that is friendly to us. Use cases in healthcare play a primary role in this discussion, as both the risks and the opportunities of new AI-based systems become particularly clear here. For example, would older people with dementia (PWD) be allowed to entrust aspects of their autonomy to AI-based assistance systems so that they may continue to independently manage other aspects of their daily lives? In this paper, we argue that the classic balancing act between the dangers and opportunities of AI in healthcare can be at least partially overcome by taking a long-term ethical approach toward a symbiotic relationship between humans and AI. We exemplify this approach by showcasing our I‑CARE system, an AI-based recommendation system for tertiary prevention of dementia. This system has been in development since 2015 as the I‑CARE Project at the University of Bremen, where it is still being researched today.} } @inproceedings{borsdorf2023SpeechEEGMatchMismatch, title={Multi-Head Attention and GRU for Improved Match-Mismatch Classification of Speech Stimulus and EEG Response}, author={Borsdorf, Marvin and Pahuja, Saurav and Ivucic, Gabriel and Cai, Siqi and Li, Haizhou and Schultz, Tanja}, booktitle={2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, year={2023}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Borsdorf2023SpeechEEGMatchMismatch.pdf}, pages={1-2}, doi={10.1109/ICASSP49357.2023.10096959}, note={Updated version}, abstract={This work is based on the participation by the HyperAttention team in the Auditory EEG Decoding Challenge, 2023 (ICASSP 2023 Signal Processing Grand Challenge) task 1, which deals with the match-mismatch classification of speech stimuli and EEG responses of human listeners. We demonstrate the benefits of using mel-spectrograms instead of speech envelopes as input features as well as the effectiveness of Multi-Head Attention and GRU for EEG and speech processing. With a total score of 79.05 %, we reach the second place in the challenge.} } @article{shi2023ppg2abp, title ={Hybrid Modeling on Reconstitution of Continuous Arterial Blood Pressure Using Finger Photoplethysmography}, author = {Shi, Wenying and Zhou, Congcong and Zhang, Yiming and Li, Kaitai and Ren, Xianglin and Liu, Hui and Ye, Xuesong}, journal = {Biomedical Signal Processing and Control}, volume = {85}, pages = {104972}, year = {2023}, issn = {1746-8094}, doi = {https://doi.org/10.1016/j.bspc.2023.104972}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/ShiZhouZhangLiRenLiuYe_BSPC2023.pdf}, abstract = {The continuous estimation of arterial blood pressure (ABP) waveforms directly from single-channel photoplethysmography (PPG) signals will predictably change the way to monitor blood pressure in the future. This article proposed a new hybrid mathematical model for continuous blood pressure monitoring by investigating the relationship between the finger PPG signal and the radial ABP signal based on a public database. Considering potential damping factors and wave propagation/reflection in blood circulation, we combined the electrical network model with the tube-load model. The optimal range of model parameters was obtained through the system identification method to realize the individualized continuous blood pressure measurements. Compared with the invasive measurement, the hybrid model performed superior blood pressure estimation with high consistency. The estimated ABP waveforms correlated highly with the reference waveforms with an average correlation coefficient of 0.96. The mean absolute error/standard deviation of the estimated systolic blood pressure (SBP), mean arterial blood pressure (MAP), and diastolic blood pressure (DBP) were 3.0/4.4, 2.1/3.0 and 2.1/3.2 mmHg, respectively. The results met the requirements of the Association for the Advancement of Medical Instrumentation (AAMI). The hybrid model is expected to be embedded in small wearable devices to directly estimate the continuous blood pressure waveforms at the radial artery site through the PPG signals, pioneering the synchronous non-sensing monitoring on blood pressure and blood flow.} } @inproceedings{steinert21_interspeech, author={Lars Steinert and Felix Putze and Dennis Küster and Tanja Schultz}, title={{Audio-Visual Recognition of Emotional Engagement of People with Dementia}}, year=2021, booktitle={Proc. Interspeech 2021}, pages={1024--1028}, doi={10.21437/Interspeech.2021-567}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/steinert21_interspeech.pdf} } @INPROCEEDINGS{Scheck2023STEGAN, author={Kevin Scheck and Tanja Schultz}, title={{STE-GAN: Speech-to-Electromyography Signal Conversion using Generative Adversarial Networks}}, year=2023, booktitle={Proc. INTERSPEECH 2023}, pages={1174--1178}, doi={10.21437/Interspeech.2023-174}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ScheckSchultz-Interspeech23.pdf}, abstract={With Speech-to-Electromyography Generative Adversarial Network (STE-GAN), we propose a model which can synthesize Electromyography (EMG) signals from acoustic speech. We condition the generator network on representations of the spoken content obtained from a voice conversion model. Given these representations, the generator outputs an EMG signal corresponding to the articulated content of the acoustic speech in the setting of a specific EMG recording session. In comparison to previous work, STE-GAN directly generates EMG signals from acoustic speech. As it uses more speaker-independent content representations as input, it can synthesize EMG signals from speech of speakers who were unseen during training.} } @book{schultz_technische_2014a, title = {Technische {Unterstuetzung} fuer {Menschen} mit {Demenz} : {Symposium} 30.09. - 01.10.2013}, isbn = {978-3-7315-0258-6}, shorttitle = {Technische {Unterstuetzung} fuer {Menschen} mit {Demenz}}, language = {de}, publisher = {KIT Scientific Publishing}, author = {Schultz, Tanja and Putze, Felix and Kruse, Andreas}, year = {2014} } @book{liu2023sensors_har, title = {Sensors for Human Activity Recognition}, shorttitle = {Sensors for HAR}, author = {Liu, Hui and et al.}, editor = {Liu, Hui and Gamboa, Hugo and Schultz, Tanja}, publisher = {{MDPI}}, isbn = {978-3-0365-7554-4}, year = {2023}, month = {jun}, doi = {10.3390/books978-3-0365-7555-1}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/LiuGamboaSchultz_Book_Sensors_for_HAR_2023.pdf} } @inproceedings{hartmann2023har_high_level_features, title = {High-Level Features for Human Activity Recognition and Modeling}, author = {Hartmann, Yale and Liu, Hui and Schultz, Tanja}, booktitle = {Biomedical Engineering Systems and Technologies}, editor = {Ana Cec{\'i}lia A. Roque and Denis Gracanin and Ronny Lorenz and Athanasios Tsanas and Nathalie Bier and Ana Fred and Hugo Gamboa}, year = {2023}, publisher = {Springer Nature Switzerland}, address = {Cham}, pages= {141--163}, isbn = {978-3-031-38854-5}, doi = {10.1007/978-3-031-38854-5_8}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/HartmannLiuSchultz_Springer2023.pdf}, abstract = {High-Level Features (HLF) are a novel way of describing and processing human activities. Each feature captures an interpretable aspect of activities, and a unique combination of HLFs defines an activity. In this article, we propose and evaluate a concise set of six HLFs on and across the CSL-SHARE and UniMiB SHAR datasets, showing that HLFs can be successfully extracted with machine learning methods and that in this HLF-space activities can be classified across datasets as well as in imbalanced and few-shot learning settings. Furthermore, we illustrate how classification errors can be attributed to specific HLF extractors. In person-independent 5-fold cross-validations, the proposed HLFs are extracted from 68{\%} up to 99{\%} balanced accuracy, and activity classification achieves 89.7{\%} (CSL-SHARE) and 67.3{\%} (UniMiB SHAR) accuracy. Imbalanced and few-shot learning results are promising, with the latter converging quickly. In a person-dependent evaluation across both datasets, 78{\%} accuracy is achieved. These results demonstrate the possibilities and advantages of the proposed high-level, extensible, and interpretable feature space.}, } @INPROCEEDINGS{Scheck2023StreamETS, author={Kevin Scheck and Darius Ivucic and Zhao Ren and Tanja Schultz}, title={{Stream-ETS: Low-latency End-to-end Speech Synthesis from Electromyography Signals}}, year=2023, booktitle={15th ITG Conference on Speech Communication}, pages={1--5}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ScheckIvucicRenSchultz-ITG23.pdf}, note={to appear}, abstract={The electromyographic activity of articulatory muscles provides information about the speech production process. As such, Electromyography (EMG) signals are investigated for speech communication methods without acoustic speech in the context of Silent Speech Interfaces. For this, EMG-to-Speech (ETS) models predict acoustic speech from EMG signals captured during articulation. In this work, we propose Stream-ETS, a streamable end-to-end ETS system. Its architecture consists of a causal EMG encoder, processing EMG signals to Mel-spectrograms, and a causal neural vocoder, which predicts the acoustic speech signal. Using a GPU, Stream-ETS outputs acoustic speech from 10 millisecond chunks of EMG in approx. $8$ milliseconds, making the system perform in real-time with a low-latency. We first pre-train both components and then perform end-to-end fine-tuning. Experiments indicate that end-to-end training increases the naturalness of the speech synthesis.} } @INPROCEEDINGS{ablimit2023ITG, author={Ayimnisagul Ablimit and Elisa Brauße and Tanja Schultz}, title={{Screening of Alzheimer's Dementia up to 12 Years ahead from Conversational Speech of ILSE Study}}, year=2023, booktitle={15th ITG Conference on Speech Communication}, pages={1--5}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ay_ITG23.pdf}, note={to appear}, abstract={Alzheimer's disease (AD) is an incurable neurodegenerative disorder and successful symptomatic therapy requires early diagnosis. However, when the diagnosis is made by clinical screening, AD has already impaired the patient's cognitive abilities and the optimal time point for early therapy has passed. Therefore, early diagnosis of AD is crucial. Spoken language skills are strong biomarkers for detecting dementia, as they are affected in the early stages of cognitive impairment. In this work, we aim to conduct predictive screening, i.e., predict future cognitive diagnosis, using the longitudinal conversational speech corpus ILSE. We extract acoustic and linguistic features from the speech of current time measurement. We apply non-parametric significance test for group differences between healthy and AD samples in predictive screening and analyze the distribution of features in AD screening. We train models for predictive screening of AD. Our classifier achieves an Unweighted Average Recall of $83.8\%$~(in 5 years) and $82.5\%$~(in 12 years).} } @INPROCEEDINGS{Brausse2023ITG, author={{Elisa Brauße and Kevin Scheck and Tanja Schultz}}, title={{Toward Semi-supervised Transcription of NAKO+ILSE: Influence of Automatic Speech Recognition Performance on Manual Transcription Effort}}, year=2023, booktitle={15th ITG Conference on Speech Communication}, pages={106-110}, doi={10.30420/456164020}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/BrausseScheckSchultz_ITG23.pdf}, abstract={Acoustic and linguistic information of spoken communication were found to be a reliable estimator for early detection of cognitive decline. The extraction of linguistic features, however, requires transcription from spoken content to text, either manually or by automatic speech recognition~(ASR). We propose a semi-automatic transcription system using manual correction of ASR output. It is applied to our new project, with which we envision to fuse information of the Interdisciplinary Longitudinal Study of Adult Development and Aging~(ILSE) with the German National Cohort~(NAKO) study by creating a core overlap dataset NAKO+ILSE. We compare the performance of our ASR system with the zero-shot Whisper system on ILSE interview data and NAKO+ILSE test data~NI0. Due to differences in ASR performance between data sets, we analyze the effect of noise levels on ASR performance. Lastly, we analyze the influence of using ASR hypotheses as basis for manual transcriptions. With a minimum word error rate of $45.1\%$, pre-trained Whisper models do not outperform our own ASR system of $33.55\%$. However, manual transcription time is reduced by a factor of three when using Whisper large as a basis for semi-automatic transcription.} } @article{jannat2023wifi_har, title = {Efficient {Wi-Fi}-Based Human Activity Recognition Using Adaptive Antenna Elimination}, author = {Jannat, Mir Kanon Ara and Islam, Md Shafiqul and Yang, Sung-Hyun and Liu, Hui}, journal = {IEEE Access}, year = {2023}, volume = {11}, pages = {105440--105454}, doi = {10.1109/ACCESS.2023.3320069}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/JannatIslamYangLiu_IEEEAccess2023.pdf}, abstract = {Recently, Wi-Fi-based human activity recognition using channel state information (CSI) signals has gained popularity due to its potential features, such as passive sensing and adequate privacy. The movement of various body parts in between Wi-Fi signals’ propagation path generates changes in the signal reflections and refraction, which is evident from the CSI variations. In this paper, we analyzed the relationship between human activities and properties (amplitude and phase) of Wi-Fi CSI signals on multiple receiving antennas and discovered the signal properties which vary remarkably in response to human movement. The variation of the received signal among multiple antennas shows different sensitivity to human activities, directly impacting the recognition performance. Therefore, to recognize human activities with better efficiency, we proposed an adaptive antenna elimination algorithm that automatically eliminates the non-sensitive antenna and keeps the sensitive antennas following different human activities. Furthermore, the correlation of the statistical features extracted from the amplitude and phase of the selected antennas’ CSI signal was analyzed, and a sequential forward selection was utilized to find the best subset of features. Using such a subset, three machine learning algorithms were employed on two available online datasets to classify various human activities. The experimental results revealed that even when using easy-to-implement, non-deep machine learning, such as random forest, the recognition system based on the proposed adaptive antenna elimination algorithm achieved a superior classification accuracy of 99.84% (line of sight) on the StanWiFi dataset and 97.65% (line-of-sight) / 93.33% (non-line-of-sight) on another widely applied multi-environmental dataset at a fraction of the time cost, demonstrating the robustness of the proposed algorithm.} } @INPROCEEDINGS{ren2023selflearning, author={{Zhao Ren and Kevin Scheck and Tanja Schultz}}, title={{Self-learning and Active-learning for Electromyography-to-Speech Conversion}}, year=2023, booktitle={15th ITG Conference on Speech Communication}, pages={1--5}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/RenScheckSchultz2023self.pdf}, note={to appear}, abstract={Electromyography-to-Speech conversion has demonstrated its potential to synthesise speech from electromyography signals for silent speech interfaces. In this study, we specifically tackle the lack of corresponding speech samples during real-life usage of Electromyography-to-Speech. We propose a framework that combines self-learning and active-learning. It balances automatically annotating electromyography signals by predicting speech samples and using ground-truth speech targets provided by the user. The framework is validated in a set of session-independent experiments. The results demonstrate that the proposed framework is effective to improve the model performance by increasing the size of training data while lowering the required human effort to generate speech targets. This framework appears to be promising for real-life Electromyography-to-Speech.} } @INPROCEEDINGS{IvucicBCI23, author={{}}, title={{EEG-based Decoding of Auditory Attention using a Deep Attention Network: Revealing neural commonalities of selective attention across individuals}}, year=2023, booktitle={10th International Brain-Computer-Interfaces Meeting}, pages={}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Abstract.Gabriel.Ivucic_BCI2023.pdf}, abstract={Introduction: Focusing on specific sound sources in cluttered environments is crucial for daily communication. However, this ability poses a great challenge for persons that are dependent on hearing aids, as the devices do not possess information about which audio sources are interesting to the user. To solve this problem, approaches from the field of auditory attention detection (AAD) are trying to develop cognitive models of auditory selective attention using electroencephalography (EEG). Here, subject-independence (SI) is useful for EEG-applications in auditory attention detection because it eliminates the need for pretraining on specific individuals, making the model more flexible and adaptable to a wider range of users. This allows the model to be applied to new persons without the need for additional data collection and training, making it more efficient for practical applications. Such models could expand our understanding of the cognitive processes involved in selective attention. Further, an integration into hearing aids in future applications would allow individuals with hearing impairments to regain a level of normalcy in their daily activities. Materials, Methods and Results: This study aims to investigate subject-independent auditory attention decoding using electroencephalography (EEG) and Deep Neural Networks (DNN). The EEG data set in this work is publicly available and widely used in the AAD community [4.]. Participants were presented with two simultaneous but spatially separated speech stimuli, with the instruction to focus on one of the speech streams while their EEG signals were recorded with 64 channels. The decoding task is a binary classification of the attended speaker in a given time window. To achieve this, the data was preprocessed and analyzed using a Deep Attention Network [1.], which is designed to be a lightweight and efficient architecture to process raw windows of EEG signals. The network uses spatial and temporal attention modules to extract EEGchannel interactions and temporal dynamics at different frequencies. The EEG-data was lightly processed by common-average referencing and filtering the signal between 1-32 Hz, followed by segmenting in 1 second non-overlapping windows for each of the 16 participants. The network was trained to classify the attention states of the participants based on the EEG data in a leave-one-subject-out cross-validation. The results show an accuracy of 72% (STD: 11%) over all 16 participants with all but 1 participant significantly outperforming the baseline of 50%. Excluding the 6 subjects below 70% as a threshold of practical performance, the remaining 10 subjects average an 80% accuracy (STD: 6%). The extraction of the spatial maps of the network allows an insight into the importance of each channel for the classification model. The averaged electrode weights for participants reveal strongly localized activations in the prefrontal and temporal lobes (AF7, AFz, AF8, T7, T8) with an average standard deviation of 5% of the mean between the participants, for all channels. Discussion: The attention network significantly outperforms former DNN approaches for Subjectindependent auditory attention (p <.01) [3.] by an absolute of 7% (accounting for all participants) and has a lower variance between participants. While the spatial weights only reflect a part of the DNN-models, they imply a shared neural processing between the individuals in the prefrontal and temporal lobes. These areas are known to play a crucial role in speech tracking during selective listening [2.], and are likewise used by the neural network to discriminate between the different audio streams. Significance: The attention network reaches state-of-the-art performance for subject-independent auditory attention decoding with lower variability and fewer parameters while allowing an intuitive visualization of modules of the model. The ability to decode auditory attention in a subjectindependent manner is crucial for the development of cognitive models that can be applied to a wide range of individuals, including those with hearing impairments.} } @article{cai2023joystick, title = {Muscle Synergies in Joystick Manipulation}, author = {Cai, Liming and Yan, Shuhao and Ouyang, Chuanyun and Zhang, Tianxiang and Zhu, Jun and Chen, Li and Ma, Xin and Liu, Hui}, journal = {Frontiers in Physiology}, year = {2023}, volume = {14}, article-number = {1282295}, doi = {10.3389/fphys.2023.1282295}, publisher = {Frontiers Media SA}, issn = {1664-042X}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/CaiYanOuyangZhangZhuChenMaLiu_FrontiersPhysiology2023.pdf}, abstract = {Extracting muscle synergies from surface electromyographic signals (sEMGs) during exercises has been widely applied to evaluate motor control strategies. This study explores the relationship between upper-limb muscle synergies and the performance of joystick manipulation tasks. Seventy-seven subjects, divided into three classes according to their maneuvering experience, were recruited to perform the left and right reciprocation of the joystick. Based on the motion encoder data, their manipulation performance was evaluated by the mean error, standard deviation, and extreme range of position of the joystick. Meanwhile, sEMG and acceleration signals from the upper limbs corresponding to the entire trial were collected. Muscle synergies were extracted from each subject's sEMG data by non-negative matrix factorization (NMF), based on which the synergy coordination index (SCI), which indicates the size of the synergy space and the variability of the center of activity (CoA), evaluated the temporal activation variability. The synergy pattern space and CoA of all participants were calculated within each class to analyze the correlation between the variability of muscle synergies and the manipulation performance metrics. The correlation level of each class was further compared. The experimental results evidenced a positive correlation between manipulation performance and maneuvering experience. Similar muscle synergy patterns were reflected between the three classes and the structure of the muscle synergies showed stability. In the class of rich maneuvering experience, the correlation between manipulation performance metrics and muscle synergy is more significant than in the classes of trainees and newbies, suggesting that long-term training and practicing can improve manipulation performance, stability of synergy compositions, and temporal activation variability but not alter the structure of muscle synergies determined by a specific task. Our approaches and findings could be applied to 1) reduce manipulation errors, 2) assist maneuvering training and evaluation to enhance transportation safety, and 3) design technical support for sports.} } @INPROCEEDINGS{ren2023anoverview, author={Ren, Zhao and Qian, Kun and Schultz, Tanja and Schuller, Björn W.}, title={{An overview of the ICASSP special session on AI security and privacy in speech and audio processing}}, year=2023, booktitle={Proc.\ ACM Multimedia Asia Workshop}, pages={}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/ren2023anoverview.pdf}, abstract={Perceiving and producing speech and audio signals are the basic ways for humans to communicate with each other and know about the world. Benefiting from the advancement of Big Data, signal processing, and Artificial Intelligence (AI), intelligent machines have been rapidly developed to process speech and audio signals for assisting human life. Deep learning has been demonstrated to achieve excellent performance based on large amounts of data streams. In the meanwhile, the problems of security vulnerability and privacy leakage appear along with the booming technologies. Systems with security and privacy problems can expose users' personal information to danger and cause users' distrust. To facilitate technology development in tackling the aforementioned issues, the special session on ``AI security and privacy in speech and audio processing" was organised at ICASSP 2023. In this study, we provide a comprehensive overview of the invited high-quality contributions at the special session. We further discuss the current research challenges, and point out potential avenues for future works. This work is expected to summarise the research advancements and inspire more innovative studies in this area.} } @article{bian2024mllm_facial_expression, title = {Understanding Naturalistic Facial Expressions with Deep Learning and Multimodal Large Language Models}, author = {Bian, Yifan and Küster, Dennis and Liu, Hui and Krumhuber, Eva G.}, journal = {Sensors}, volume = {24}, year = {2024}, number = {1}, article-number = {126}, PubMedID = {38202988}, issn = {1424-8220}, doi = {10.3390/s24010126}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/BianKuesterLiuKrumhuber_Sesnors2024.pdf}, abstract = {This paper provides a comprehensive overview of affective computing systems for facial expression recognition (FER) research in naturalistic contexts. The first section presents an updated account of user-friendly FER toolboxes incorporating state-of-the-art deep learning models and elaborates on their neural architectures, datasets, and performances across domains. These sophisticated FER toolboxes can robustly address a variety of challenges encountered in the wild such as variations in illumination and head pose, which may otherwise impact recognition accuracy. The second section of this paper discusses multimodal large language models (MLLMs) and their potential applications in affective science. MLLMs exhibit human-level capabilities for FER and enable the quantification of various contextual variables to provide context-aware emotion inferences. These advancements have the potential to revolutionize current methodological approaches for studying the contextual influences on emotions, leading to the development of contextualized emotion models.}, } @article{liu2024biosignal_artifact, title = {Taxonomy and Real-Time Classification of Artifacts during Biosignal Acquisition: {A} Starter Study and Dataset of {ECG}}, author = {Liu, Hui and Zhang, Shiyao and Gamboa, Hugo and Xue, Tingting and Zhou, Congcong and Schultz, Tanja}, journal = {IEEE Sensors Journal}, year = {2024}, volume = {24}, number = {6}, pages = {9162--9171}, doi={10.1109/JSEN.2024.3356651}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/LiuZhangGamboaXueZhouSchultz_JSens2024.pdf}, abstract = {This article investigates electrocardiogram (ECG) acquisition artifacts often occurring in experiments due to human negligence or environmental influences, such as electrode detachment, misuse of electrodes, and unanticipated magnetic field interference, which are not easily noticeable by humans or software during acquisition. Such artifacts usually result in useless and irreparable signals; therefore, it would be a great help to research if the problems are detected during the acquisition process to alert experimenters instantly. We put forward a taxonomy of real-time artifacts during ECG acquisition, provide the simulation methods of each category, collect and share a ten-subject data corpus, and investigate machine learning solutions with a proposal of appropriate handcrafted features that reaches an offline recognition rate of 90.89% in a five-best-output person-independent leave-one-out cross-validation. We also preliminarily validate the real-time applicability of our approach.} } @inproceedings{veldanda2024emg_aur, title = {Can Electromyography Alone Reveal Facial Action Units? {A} Pilot {EMG}-Based Action Unit Recognition Study with Real-Time Validation}, author = {Veldanda, Abhinav and Liu, Hui and Koschke, Rainer and Schultz, Tanja and Küster, Dennis}, booktitle ={Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2024) - Volume 1: BIODEVICES}, pages = {142--151}, organization = {INSTICC}, publisher = {SCITEPRESS - Science and Technology Publications}, year = {2024}, isbn = {978-989-758-688-0}, issn = {2184-4305}, doi = {10.5220/0012399100003657}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/VeldandaLiuKoschkeSchultzKüster_BIODEVICES2024.pdf}, abstract = {Facial expressions play a crucial role in non-verbal and visual communication, often observed in everyday life. The facial action coding system (FACS) is a prominent framework for categorizing facial expressions as action units (AUs), which reflect the activity of facial muscles. This paper presents a proof-of-concept study for upper face action unit recognition (AUR) using electromyography (EMG) data. The study recorded facial EMG data of a subject over four sessions, who imitated facial expressions corresponding to four different AUs. The subject-dependent models that were trained achieved high accuracy in near-real time and were able to classify AUs not directly underneath the recording sites.} } @inproceedings{wang2024eeg_exoskeleton, title = {Comfort Assessment Method of {EEG}-Based Exoskeleton Walking-Assistive Device}, author = {Wang,Heyuan and Li, Kaitai and Liu, Hui and Ye, Xuesong and Zhou, Congcong}, booktitle = {Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2024) - Volume 1: BIOSIGNALS}, pages = {675--682}, organization = {INSTICC}, publisher = {SCITEPRESS - Science and Technology Publications}, year = {2024}, isbn = {978-989-758-688-0}, issn = {2184-4305}, doi = {10.5220/0012564800003657}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/WangLiLiuYeZhou_BIOSIGNALS2024.pdf}, abstract = {The study of wearable exoskeleton robotics has garnered significant attention, amidst a rapidly expanding corpus of scholarly work aimed at the empirical evaluation of the performance characteristics of robotic exoskeletons. However, quantifying comfort performance is still a significant and challenging task. This study aimed to perform comfort assessment based on EEG (Electroencephalography) signals and classical machine learning models as well as deep learning model. It involved collecting EEG data from users wearing lower limb exoskeleton walking-assistive devices for comfort assessment during walking experiments. The subjective evaluation labels of comfort were obtained using a semantic differential scale, providing comfort labels data for each participant in each trial. This study conducted a comparative analysis of three classical ML (Machine Learning) models, Naive Bayes, K-Nearest Neighbors, and Support Vector Machine models, with DL (Deep Learning) model, LSTM (Long Short-Term Memory), in terms of their accuracy for comfort assessment. The results of the analysis showed that the deep learning model, LSTM, outperformed the classical machine learning models, in terms of accuracy for evaluating comfort. Specifically, we get an accuracy of 0.91±0.12 on the LSTM model. The LSTM model demonstrated higher accuracy and better performance in capturing complex patterns and relationships within the EEG data, leading to the potential of more accurate predictions of comfort levels.} } @inproceedings{cai2024muscle_synergies, author = {Cai, Liming and Yan, Shuhao and Ouyang, Chuanyun and Zhang, Tianxiang and Zhu, Jun and Chen, Li and Liu, Hui}, title = {Associating Endpoint Accuracy and Similarity of Muscle Synergies}, booktitle = {Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2024) - Volume 1: BIOSIGNALS}, pages = {683--694}, organization = {INSTICC}, publisher = {SCITEPRESS - Science and Technology Publications}, year = {2024}, isbn = {978-989-758-688-0}, issn = {2184-4305}, doi = {10.5220/0012586800003657}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/CaiYanOuyangZhangZhuChenLiu_BIOSIGNALS2024.pdf}, abstract = {Recently, extracting muscle synergy from surface electromyographic (sEMG) signals has become a standard method for evaluating motor control strategies during exercise. The synergy of the upper extremity in various stretch and reach tasks has been described in many studies. However, few of them have analyzed the relationship between task performance and muscle synergy. This study provides an experimental device and analysis method for muscle coordination in the joystick task for the specific action of the pilots' joystick manipulation. Eight healthy subjects performed the joystick manipulation. For the upper limbs, the task involved isotonic exercises with three different load levels, during which EMG and acceleration data from ten muscles were recorded. The muscle synergy effect was extracted, and the correlation between muscle synergy similarity, manipulation performance, and interaction load was studied. The experimental data showed that manipulation performance varied under different loading conditions, but there were no significant changes in the synergistic muscle structure. We found significant correlations between the similarity of some synergistic muscle structures and manipulation performance. However, there was no strong correlation between individual action performance and the average similarity of their muscle synergy. Through the analysis of muscle synergy, we can determine that there is a fixed muscle synergy pattern during rocker manipulation, of which the structure is independent of the rocker load level, and muscle synergy similarity was negatively correlated with manipulation performance. The results of this study contribute to improving the ergonomics of the flight stick and propose targeted muscle training methods to enhance the precision of flight maneuvers.} } @inproceedings{cao2024driver_pose, title = {Integrated Driver Pose Estimation for Autonomous Driving}, author = {Cao, Xiao and Hu, Wei and Liu, Hui}, booktitle = {Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2024) - Volume 1: BIOSIGNALS}, pages = {695--702}, organization = {INSTICC}, publisher = {SCITEPRESS - Science and Technology Publications}, year = {2024}, isbn = {978-989-758-688-0}, issn = {2184-4305}, doi = {10.5220/0012639400003657}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/CaoHuLiu_BIOSIGNALS2024.pdf}, abstract = {Human-machine interaction, especially driver posture estimation is important to the development of autonomous driving, which can facilitate safe and smooth driving behaviours. Besides, it also contributes to ergonomics research and human-machine interaction design for automated vehicles. The existing studies have got great achievements in body estimation, hand pose estimation, and even face feature estimation thanks to the rapid development of deep learning approaches and the upgrade of hardware equipment. However, most existing models can only process body estimation or hand estimation separately, which will impede the research on driver-vehicle interaction in autonomous driving. This is because the driving process is highly dependent on the cooperation between the body and hands behaviours. In this study, five popular deep learning models, including Simple Faster R-CNN, RootNet, PoseNet, Yolo v3, and graph convolutional neural network, are combined through a cascade method to develop an integrated model which can estimate body and hand simultaneously during the driving process. The coordinate transform system is proposed to connect models in series. Experiment results demonstrate the proposed method can produce 2D and 3D reorganization of the human body and hands simultaneously with acceptable accuracy.} } @inproceedings{zhang2024motivation_drop, title = {Really Can't Hold On Anymore? {Physiological} Indicators Versus Self-Reported Motivation Drop during Jogging}, author = {Zhang, Shiyao and Kolensnikov, Sergei and Rennspieß, Till and Porzel, Robert and Schultz, Tanja and Liu, Hui}, booktitle = {Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2024) - Volume 1: BIOSIGNALS}, pages = {821--831}, organization = {INSTICC}, publisher = {SCITEPRESS - Science and Technology Publications}, year = {2024}, isbn = {978-989-758-688-0}, issn = {2184-4305}, doi = {10.5220/0012577300003657}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/ZhangKolensnikovRennSpießPorzelSchultzLiu_BIOSIGNALS2024.pdf}, abstract = {Motivational dynamics in jogging constitute a pivotal factor influencing a runner's performance, persistence, and overall engagement in the running activity. The manifestation of diminished motivation is concomitant with a cascade of physiological responses, capable of being represented through biological signals, for which biosignal monitoring, a common practice in evaluating athletic performance, emerges as a valuable tool. Should biosignals, as dynamic indicators during exercise, exhibit discernible shifts correlating with changes in motivation, the prospect of actively modulating motivation levels and intervening in athletes' performance during exercise becomes feasible. This study consists of collecting comprehensive biological data, including electrocardiogram (ECG), surface electromyogram (sEMG), and respiration signals (RSP), from runners who participated in a 20-minute running session. Participants were asked to self-report a decrease in motivation during jogging. Using heart rate variability analysis, self-similarity matrix and deep learning methodologies, this work seeks to explore whether the discomforts reported and triggered by decreased motivation had discernible effects on monitored physiological signals, thus advancing our understanding of the nuanced relationship between physiological responses and motivational states in running.} } @book{biostec2024, title = {Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies – (Volume 1)}, shorttitle = {Proceedings of BIOSTEC 2024}, author = {Yousef, Malik and Liu, Hui and Gamboa, Hugo and et al.}, editor = {Guarino, Maria Pedro and Hotta Kazuhiro and Yousef, Malik and Liu, Hui and Saggio, Giovanni and Fred, Ana and Gamboa, Hugo}, publisher = {{INSTICC}}, isbn = {978-989-758-688-0}, issn = {2184-4305}, year = {2024}, month = {mar}, doi = {10.5220/0000184700003657}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/BIOSTEC_2024_Proceedings_Volume1.pdf} } @article{furk2024cardiorespiratory, author = {Furk, Dania and Silva, Luís and Dias, Mariana and Fujão, Carlos and Probst, Phillip and Liu, Hui and Gamboa, Hugo}, title = {Cardiorespiratory Response to Workload Volume and Ergonomic Risk: Automotive Assembly Line Operators’ Adaptations}, journal = {Applied Sciences}, volume = {14}, year = {2024}, number = {9}, article-number = {3921}, issn = {2076-3417}, abstract = {Repetitive tasks can lead to long-term cardiovascular problems due to continuous strain and inadequate recovery. The automobile operators on the assembly line are exposed to these risks when workload volume changes according to the workstation type. However, the current ergonomic assessments focus primarily on observational and, in some cases, biomechanical methods that are subjective and time-consuming, overlooking cardiorespiratory adaptations. This study aimed to analyze the cardiorespiratory response to distinct workload volumes and ergonomic risk (ER) scores for an automotive assembly line. Sixteen male operators (age = 38 ± 8 years; BMI = 25 ± 3 kg·m2) volunteered from three workstations (H1, H2, and H3) with specific work cycle duration (1, 3, and 5 min respectively). Electrocardiogram (ECG), respiratory inductance plethysmography (RIP), and accelerometer (ACC) data were collected during their shift. The results showed significant differences from the first to the last 10 min, where H3 had its SDRRi reduced (p = 0.014), H1’s phase synchrony and H2’s coordination between thoracic and abdominal movements decreased (p < 0.001, p = 0.039). In terms of ergonomic risk, the moderate-high rank showed a reduction in SDRRi (p = 0.037) and moderate-risk activities had diminished phase synchrony (p = 0.018) and correlation (p = 0.004). Thus, the explored parameters could have the potential to develop personalized workplace adaptation and risk assessment systems.}, doi = {10.3390/app14093921}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/FurkSilvaDiasFujaoProbstLiuGamboa_Applied_Science_2024.pdf} } @INPROCEEDINGS{Lankenau2024Multimodal, author={{Kim Marie Lankenau and Elisa Brauße and Jana Schill and Jochen Hirsch and Johannes Schröder and Matthias Günther and Tanja Schultz}}, title={Multimodal Dementia Screening from Brain Magnetic Resonance Imaging and Conversational Speech}, year=2024, booktitle={46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Lankenau_Brausse_etal_EMBC24.pdf}, note={to appear}, abstract={Early detection of Alzheimer's dementia is crucial for effective symptomatic treatment. Herein, we explore the opportunities of dementia screening based on automatically derived biomarkers from Magnetic Resonance Imaging (MRI) and spoken communication. In particular, we compare the screening performance of unimodal MRI-based or speech-based markers with their multimodal counterparts. We use structural MRI data and interview recordings from the Interdisciplinary Longitudinal Study on Adult Development and Aging to analyze state and predictive screening between participants with and without cognitive impairment. We assess the effect of varying training set sizes on unimodal screening performance and compare screening performance of unimodal data with multimodal data, which are combined through Early, Late and Tensor Fusion. For both state and predictive screening, classifiers that combined both modalities with the Early Fusion method outperformed the single modalities, achieving an Unweighted Average Recall of $83.2\%$ and $74.9\%$, respectively. On the evaluated dataset, markers derived from speech are just as useful for predictive screening as markers derived from MRI.} } @conference{hartmann2024a, author={Yale Hartmann. and Jonah Klöckner. and Lucas Deichsel. and Rinu Paul. and Tanja Schultz.}, title={Gait Parameter Estimation from a Single Privacy Preserving Depth Sensor}, booktitle={Proceedings of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies - BIOSIGNALS}, year={2024}, pages={637-645}, publisher={SciTePress}, organization={INSTICC}, doi={10.5220/0012383700003657}, isbn={978-989-758-688-0}, issn={2184-4305}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/123837.pdf} } @article{zhang2024eeg_emotion, author = {Zhang, Xinyi and Cheng, Xiankai and Liu, Hui}, title = {{TPRO-NET}: {An} {EEG}-Based Emotion Recognition Method Reflecting Subtle Changes in Emotion}, journal = {Scientific Reports}, volume = {14}, article-number = {13491}, year = {2024}, issn = {2045-2322}, abstract = {Emotion recognition based on Electroencephalogram (EEG) has been applied in various fields, including human–computer interaction and healthcare. However, for the popular Valence-Arousal-Dominance emotion model, researchers often classify the dimensions into high and low categories, which cannot reflect subtle changes in emotion. Furthermore, there are issues with the design of EEG features and the efficiency of transformer. To address these issues, we have designed TPRO-NET, a neural network that takes differential entropy and enhanced differential entropy features as input and outputs emotion categories through convolutional layers and improved transformer encoders. For our experiments, we categorized the emotions in the DEAP dataset into 8 classes and those in the DREAMER dataset into 5 classes. On the DEAP and the DREAMER datasets, TPRO-NET achieved average accuracy rates of 97.63%/97.47%/97.88% and 98.18%/98.37%/98.40%, respectively, on the Valence/Arousal/Dominance dimension for the subject-dependent experiments. Compared to other advanced methods, TPRO-NET demonstrates superior performance.}, doi = {10.1038/s41598-024-62990-4}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/ZhangChengLiu_SR2024.pdf} } @inproceedings{zhang2024avatar, author = {Zhang, Shiyao and Faruk, Omar and Porzel, Robert and Küster, Dennis and Schultz, Tanja and Liu, Hui}, booktitle = {2024 International Conference on Activity and Behavior Computing (ABC)}, title = {Examining the Effects of Human-Likeness of Avatars on Emotion Perception and Emotion Elicitation}, year = {2024}, organization={IEEE}, pages = {1-12}, abstract = {Digital communication has become a fundamental part of our daily interactions and professional pursuits. An increasing number of online interaction settings now provide the possibility to visually represent oneself via an animated avatar instead of a video stream. Benefits include protecting the communicator's privacy while still providing a means to express their individuality. In consequence, there has been a surge in means for avatar-based personalization, ranging from classic human representations to animals, food items, and more. However, using avatars also has drawbacks. Depending on the human-likeness of the avatar and the corresponding disparities between the avatar and the original expresser, avatars may elicit discomfort or even hinder effective nonverbal communication by distorting emotion perception. This study examines the relationship between the human-likeness of virtual avatars and emotion perception for Ekman's six “basic emotions,” which are anger, disgust, fear, happiness, sadness, and surprise. Research reveals that avatars with varying degrees of human-likeness have distinct effects on emotion perception. High human-likeness avatars, such as human avatars, tend to elicit more negative emotional responses from users, a phenomenon that is consistent with the concept of Un-canny Valley in aesthetics, which suggests that closely resembling humans can provoke negative emotional responses. Conversely, a raccoon avatar and a shark avatar, known as cuteness, which exhibit moderate human similarity in this study, demonstrate a positive influence on emotion perception. Our initial results suggest that the human-likeness of avatars is an important factor for emotion perception. The results from the follow-up study further suggest that the cuteness of avatars and their natural facial status may also play a significant role in emotion perception and elicitation. We discuss practical implications for strategically conveying specific human behavioral messages through avatars in multiple applications, such as business and counseling.}, doi={10.1109/ABC61795.2024.10652090}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/ZhangFarukPorzelKuesterSchultzLiu_ABC2024.pdf} } @article{liu2024sensors_har_editorial, author = {Liu, Hui and Gamboa, Hugo and Schultz, Tanja}, title = {Human Activity Recognition, Monitoring, and Analysis Facilitated by Novel and Widespread Applications of Sensors}, journal = {Sensors}, volume = {24}, year = {2024}, number = {16}, article-number = {5250}, issn = {1424-8220}, doi = {10.3390/s24165250}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/LiuGamboaSchultz_Editorial_Sensors2024.pdf} } @article{li2024extrapolation_muscle_excitations, author = {Li, Kaitai and Wang, Daming Wang and Chen, Zuobing and Guo, Dazhi and Pan, Shuyi and Liu, Hui and Zhou, Congcong and Ye, Xuesong}, title = {Template-based synergy extrapolation analysis for prediction of muscle excitations}, journal = {Physiological Measurement}, year = {2024}, issn = {1361-6579}, abstract = {Objective: Accurate prediction of unmearsured muscle excitations can reduce the required wearable surface electromyography (sEMG) sensors, which is a critical factor in the study of physiological measurement. Synergy extrapolation uses synergy excitations as building blocks to reconstruct muscle excitations. However, the practical application of synergy extrapolation is still limited as the extrapolation process utilizes unmeasured muscle excitations it seeks to reconstruct. This paper aims to propose and derive methods to provide an avenue for the practical application of synergy extrapolation with non-negative matrix factorization (NMF) methods. Approach: Specifically, a tunable Gaussian-Laplacian mixture distribution NMF (GLD-NMF) method and related multiplicative update rules are derived to yield appropriate synergy excitations for extrapolation. Furthermore, a template-based extrapolation structure (TBES) is proposed to extrapolate unmeasured muscle excitations based on synergy weighting matrix templates totally extracted from measured sEMG datasets, improving the extrapolation performance. Moreover, we applied the proposed GLD-NMF method and TBES to selected muscle excitations acquired from a series of single-leg stance (SLS) tests, walking tests and upper limb reaching tests. Main results: Experimental results show that the proposed GLD-NMF and TBES could extrapolate unmeasured muscle excitations accurately. Moreover, introducing synergy weighting matrix templates could decrease the number of sEMG sensors in a series of experiments. In addition, verification results demonstrate the feasibility of applying synergy extrapolation with NMF methods. Significance: With the TBES method, synergy extrapolation could play a significant role in reducing data dimensions of sEMG sensors, which will improve the portability of sEMG sensors-based systems and promotes applications of sEMG signals in human-machine interfaces scenarios.}, doi = {10.1088/1361-6579/ad7776}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/LiWangChenGuoPanLiuZhouYe_PMEA2024.pdf} } @inproceedings{liu2024mora, author = {Liu, Hui and Flaack, Leon and Zhang, Shiyao and Schultz, Tanja}, booktitle = {Artificial Neural Networks and Machine Learning -- ICANN 2024}, title = {{LSTM-MorA}: {Melody}-Accompaniment Classification of {MIDI} Tracks}, year = {2024}, publisher = {Springer Nature Switzerland}, address = {Cham}, pages = {443-458}, isbn = {978-3-031-72356-8}, abstract = {Many studies based on symbolic music signals require retaining only melody tracks or accompaniment tracks from musical instrument digital interface (MIDI) files. However, this seemingly simple setting often becomes a stumbling block in the first step because the MIDI format does not have any mandatory regulations for the track numbers of melody/accompaniment tracks. This study delves into the classification of melody and accompaniment parts within MIDI files, pioneering the use of long-short-term memory (LSTM) for this purpose. An LSTM network is trained to classify multivariate time series of varying lengths, representing the tracks within MIDI files as either melody or accompaniment. Experimental results of over 0.91 accuracy, precision, recall and F score reveal that our proposed methodology, LSTM-MorA (Melody or Accompaniment), could be one of the solutions for MIDI melody-accompaniment classification.}, doi={10.1007/978-3-031-72356-8_29}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/LiuFlaackZhangSchultz_ICANN2024.pdf} } @inproceedings{borsdorf2024wTIMIT2mix, title={{wTIMIT2mix: A Cocktail Party Mixtures Database to Study Target Speaker Extraction for Normal and Whispered Speech}}, author={Borsdorf, Marvin and Pan, Zexu and Li, Haizhou and Schultz, Tanja}, booktitle={{Proceedings of the 25th Annual Conference of the International Speech Communication Association (INTERSPEECH)}}, year={2024}, pages={5038--5042}, doi={10.21437/Interspeech.2024-1172}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Borsdorf2024wTIMIT2mix.pdf}, abstract={Target speaker extraction (TSE) seeks to single out a target speaker's voice from a given speech mixture signal with the help of a target reference signal. This algorithm enables novel speech applications such as smart hearing aids. A TSE system has to work reliably in any everyday conversational situation. This may also include speakers who switch naturally between normal and whispered speech modes. This work represents the first attempt to perform TSE for whispered speech. For this, we construct a new first of its kind database, called wTIMIT2mix, which comprises two-speaker speech mixtures and target speaker reference signals given in both normal and whispered speech modes. Our results on TSE show that if these conditions are included in the training, a model can be equipped to work under all closed-set conditions.}, } @inproceedings{ewert2024Lombard-GRID-2mix, title={{Does the Lombard Effect Matter in Speech Separation? Introducing the Lombard-GRID-2mix Dataset}}, author={Ewert, Iva and Borsdorf, Marvin and Li, Haizhou and Schultz, Tanja}, booktitle={{Proceedings of the 25th Annual Conference of the International Speech Communication Association (INTERSPEECH)}}, year={2024}, pages={577--581}, doi={10.21437/Interspeech.2024-1131}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Ewert2024Lombard-GRID-2mix.pdf}, abstract={Inspired by the human ability of selective listening, speech separation aims to equip machines with the capability to disentangle cocktail party soundscapes into the individual sound sources. Recently, neural network based algorithms have been studied to work reliably under various conditions. However, to the best of our knowledge, a change in the speaking style has not yet been studied. The Lombard effect, a reflexive change in speaking style triggered by noisy environments, is a typical behavior in everyday conversational situations. In this work, we introduce a new first of its kind dataset, called Lombard-GRID-2mix, to study speech separation for two-speaker mixtures on normal speech and Lombard speech. In a comprehensive study, we show that speech separation systems can be equipped to work for both normal speech and Lombard speech. We apply a carefully designed finetuning method to enable the system to work even if noise is present in the Lombard speech for different SNR ratios.}, } @article{borsdorf2024OJSP, author = {Borsdorf, Marvin and Cai, Siqi and Pahuja, Saurav and De Silva, Dashanka and Li, Haizhou and Schultz, Tanja}, title = {Attention and Sequence Modeling for Match-Mismatch Classification of Speech Stimulus and EEG Response}, journal = {IEEE Open Journal of Signal Processing}, volume = {5}, year = {2024}, number = {}, article-number = {}, issn = {}, pages={799-809}, doi = {10.1109/OJSP.2023.3340063}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/Borsdorf2024OJSP.pdf}, abstract = {For the development of neuro-steered hearing aids, it is important to study the relationship between a speech stimulus and the elicited EEG response of a human listener. The recent Auditory EEG Decoding Challenge 2023 (Signal Processing Grand Challenge, IEEE International Conference on Acoustics, Speech and Signal Processing) dealt with this relationship in the context of a match-mismatch classification task. The challenge's task was to find the speech stimulus that elicited a specific EEG response from two given speech stimuli. Participating in the challenge, we adopted the challenge's baseline model and explored an attention encoder to replace the spatial convolution in the EEG processing pipeline, as well as additional sequence modeling methods based on RNN, LSTM, and GRU to preprocess the speech stimuli. We compared speech envelopes and mel-spectrograms as two different types of input speech stimulus and evaluated our models on a test set as well as held-out stories and held-out subjects benchmark sets. In this work, we show that the mel-spectrograms generally offer better results. Replacing the spatial convolution with an attention encoder helps to capture better spatial and temporal information in the EEG response. Additionally, the sequence modeling methods can further enhance the performance, when mel-spectrograms are used. Consequently, both lead to higher performances on the test set and held-out stories benchmark set. Our best model outperforms the baseline by 1.91% on the test set and 1.35% on the total ranking score. We ranked second in the challenge.} } @book{liu2025sensors_har, title = {Sensors for Human Activity Recognition II}, shorttitle = {Sensors for HAR II}, author = {Liu, Hui and et al.}, editor = {Liu, Hui and Gamboa, Hugo and Schultz, Tanja}, publisher = {{MDPI}}, isbn = {978-3-7258-2804-3}, year = {2025}, month = {jann}, doi = {10.3390/books978-3-7258-2804-3}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/LiuGamboaSchultz2025_Sensors_for_HAR_II_Book.pdf} } @article{xiang2025_microdroplet_flow, author = {Xiang, Lanting and Solarczek, Jennifer and Krajka, Victor and Liu, Hui and Ahlborn, Lina and Schallmey, Anett and Constantinou, Iordania}, title = {Evaluating the Potential of Microdroplet Flow in Two-Phase Biocatalysis: A Systematic Study}, journal = {ACS Applied Materials \& Interfaces}, year = {2025}, volume = {17}, number = {3}, issn = {4776-4787}, abstract = {Two-phase biocatalysis in batch reactions often suffers from inefficient mass transfer, inconsistent reaction conditions, and enzyme inactivation issues. Microfluidics offer uniform and controlled environments ensuring better reproducibility and enable efficient, parallel processing of many small-scale reactions, making biocatalysis more scalable. In particular, the use of microfluidic droplets can increase the interfacial area between the two phases and can therefore also increase reaction rates. For these reasons, slug flow has been extensively used in two-phase biocatalysis in recent years. However, microdroplet flow has been largely neglected for this application despite its great potential. In this work, we performed biphasic biocatalysis in microfluidic droplets, both in microdroplets and slugs, as well as in batch, and systematically investigated the effect of various reaction parameters on the outcome of the reaction. We show that microdroplet flow outperforms the more commonly used batch and slug flow configurations for most reaction conditions by providing shorter substrate diffusion paths and larger interfacial area for the reaction. The potential trade-off between maximized mass transfer and possibly higher enzyme inactivation rates in small droplets with large surface-to-volume ratios was also investigated for the first time, and a pipeline was established to allow evaluation in other reactions. Finally, the effect of surfactant necessary for microdroplet stabilization was also investigated in all reaction setups for the first time, and it was shown that a properly selected surfactant can have a positive effect at low concentrations by creating more stable emulsions and smaller droplets, thus increasing the interfacial area between the two phases.}, doi = {10.1021/acsami.4c15647}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/XiangSolarczekKrajkaLiuAhlbornSchallmeyConstantinou2025_ACS_Appl_Mater_Interfaces.pdf} } @inproceedings{kuester2025emg_size, //note = {Best Paper Award}, title = {The Bigger the Better? {T}owards {EMG}-Based Single-Trial Action Unit Recognition of Subtle Expressions}, author = {Küster, Dennis and Rammohan, Rathi Adarshi and Liu, Hui and Schultz, Tanja and Koschke, Rainer}, booktitle = {Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2025) - Volume 1: BIODEVICES}, pages = {100--110}, organization = {INSTICC}, publisher = {SciTePress}, year = {2025}, isbn = {978-989-758-731-3}, issn = {2184-4305}, doi = {}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/KusterRammohanLiuSchultzKoschke_BIODEVICES2025.pdf}, abstract = {Facial expressions are at the heart of everyday social interaction and communication. Their absence, such as in Virtual Reality settings, or due to conditions like Parkinson’s disease, can significantly impact communication. Electromyography (EMG)-based facial action unit recognition (AUR) offers a sensitive and privacy-preserving alternative to video-based methods. However, while prior research has focused on peak intensity action units (AUs), there has been a lack of research on EMG-based AURs for lightweight recording of subtle expressions at multiple muscle sites. This study evaluates EMG-based AUR for both low- and high-intensity expressions across eight AUs using two types of mobile electrodes connected to the Biosignal Plux system. The results of four subjects indicate that even limited data may be sufficient to train reasonably accurate AUR models. Larger snap-on electrodes performed better for peak-intensity AUs, but smaller electrodes resulted in higher performance for low-intensity expressions. These findings suggest that EMG-based AUR is viable for subtle expressions from short data segments and that smaller electrodes hold promise for future applications.} } @inproceedings{Paul2025longitudinal_data, title = {Longitudinal Data Acquisition for AI Services in Long-Term Care Facilities for Older Adults}, author = {Paul, Rinu Elizabeth and Kock, Pantea and Hartmann, Yale and Ball, Eckhard and Seibert, Kathrin and Liu, Hui and Schultz, Tanja}, booktitle = {Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2025) - Volume 2: HEALTHINF}, pages = {1099--1110}, organization = {INSTICC}, publisher = {SciTePress}, year = {2025}, isbn = {978-989-758-731-3}, issn = {2184-4305}, doi = {}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/PaulKockHartmannBallSeibertLiuSchultz_HealthInf2025.pdf}, abstract = {Data is essential for analysis, processing, feature extraction, and machine learning models, serving as a cornerstone for developing patient-centered digital health technologies for older adults. Most datasets in older adult applications are collected in controlled laboratories, with fewer from natural environments. Data Collection and processing in natural settings is challenging, often yielding both usable and unusable data. This paper focuses on collecting data from older residents in long-term care facilities using sensor boxes installed in resident rooms. The sensor box, equipped with a depth sensor, captures depth images around the clock. We collected continuous 24-hour depth images from 45 older residents in nursing homes over 15 months. We describe the ethical, social, and technical conditions for collecting on-site data from depth sensors in nursing homes. We propose a pipeline to process depth images and classify them into different room states and corrupted frames using machine learning models, achieving 93% accuracy in occupied room classification. Using this dataset, we aim to develop AI services such as fall detection, activity monitoring, gait analysis, sleep position monitoring, and bed exits in long-term care facilities. These insights advance digitally enabled care solutions for older adults, paving the way for innovative, sustainable strategies.} } @inproceedings{borsdorf2025SpeechSeparationLowResource, title={{Speech Separation for Low-Resource Languages}}, author={Borsdorf, Marvin and Pan, Zexu and Himmelmann, Pascal and Li, Haizhou and Schultz, Tanja}, booktitle={{2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}}, year={2025}, pages={1-5}, doi={10.1109/ICASSP49660.2025.10888872}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Borsdorf2025SpeechSeparationLowResource.pdf}, abstract={Speech separation aims to equip machines with the human ability of selective listening, i.e. to focus attention on specific information in spoken communication. Studies have shown that the language spoken in a cocktail party scenario matters. While the development of speech separation models can leverage extensive databases, for the majority of languages only very limited data is available. This work presents the very first study on speech separation for low-resource languages. We choose blind source separation as the task to be studied and analyze three strategies to overcome the data scarcity of two low-resource languages from the GlobalPhoneMS2 database. We show that data from other languages can be used to develop models that work for low-resource languages. Finetuning additionally boosts the performance, and training on multiple languages increases both performance and robustness. We show that dynamic mixing in the development helps to find a trade-off between performance and development time.}, } @inproceedings{Mendil2021GlareEffect, author={Mendil, Anthony and Salous, Mazen and Putze, Felix}, booktitle={2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)}, title={Behaviour-based detection of Transient Visual Interaction Obstacles with Convolutional Neural Networks and Cognitive User Simulation}, year={2021}, organization={IEEE}, volume={}, number={}, pages={3348-3355}, doi={10.1109/SMC52423.2021.9659065}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Mendil2021GlareEffect.pdf}, abstract={The performance of humans interacting with computers can be impaired by several obstacles. Such obstacles are called Human Computer Interaction (HCI) obstacles. In this paper, we present an approach of detecting a transient visual HCI interaction obstacle called glare effect from logged user behaviour during system use. The glare effect describes a scenario in which sunlight shines onto the display, resulting in less distinguishable colors. For the detection of this obstacle one and two dimensional convolutional neural networks (1D convnets and 2D convnets) are utilized. The 1D convnet decides based on temporal sequences while the 2D convnet uses synthetic images created with those sequences. In order to increase the available training data a cognitive user simulator is used that implements a generative optimization algorithm to simulate behavioural data. Four ensemble-based systems are implemented, one each for 5, 10, 15 and 20 game rounds. The first two are based on 1D and the other two on 2D convnets. Each system consists of multiple models voting for the final prediction. The accuracies of these systems in the order of the number of rounds are 72.5%, 82.5%, 80% and 85%}, } @inproceedings{Richardson2025Cognifuse, author={Richardson, Anthony and Beetz, Michael and Schultz, Tanja and Putze, Felix}, booktitle={Proceedings of the 47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2025)}, title={CogniFuse and Multimodal Deformers: A Unified Approach for Benchmarking and Modeling Biosignal Fusion}, year={2025}, volume={}, number={}, pages={}, doi={}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Richardson2025Cognifuse.pdf}, abstract={Continuously monitored physiological signals carry rich information about the human body and the biological processes happening within. Extracting this information from casually collected biosignal data in activities of daily living holds great potential for real-time monitoring of physical and mental states, but comes with increased difficulty due to the influence of noise and artifacts. Thus, we create CogniFuse, the first publicly available multi-task benchmark for multimodal biosignal fusion in such challenging environments. For many biosignals, especially electrophysiological signals, the information contained in different frequency bands plays a significant role in analyzing the physiological states of the body. Therefore, we introduce a group of novel fusion models, called Multimodal Deformers, that capture multi-level power features as well as long- and short-term temporal dependencies in multimodal biosignal data. In particular, our proposed Multi-Channel Deformer achieves the highest average benchmark score, outperforming all models of comparison. To assure full transparency and reproducibility, and to support future research on multimodal biosignal fusion, all code and data is made publicly available.}, } @inproceedings{Richardson2025MoDiffAE, author={Richardson, Anthony and Putze, Felix}, booktitle={Proceedings of the 27th International Conference on Multimodal Interaction (ICMI ’25)}, title={Motion Diffusion Autoencoders: Enabling Attribute Manipulation in Human Motion Demonstrated on Karate Techniques}, year={2025}, volume={}, number={}, pages={}, doi={10.1145/3716553.3750773}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Richardson2025MoDiffAE.pdf}, abstract={Attribute manipulation deals with the problem of changing individual attributes of a data point or a time series, while leaving all other aspects unaffected. This work focuses on the domain of human motion, more precisely karate movement patterns. To the best of our knowledge, it presents the first success at manipulating attributes of human motion data. One of the key requirements for achieving attribute manipulation on human motion is a suitable pose representation. Therefore, we design a novel continuous, rotation-based pose representation that enables the disentanglement of the human skeleton and the motion trajectory, while still allowing an accurate reconstruction of the original anatomy. The core idea of the manipulation approach is to use a transformer encoder for discovering high-level semantics, and a diffusion probabilistic model for modeling the remaining stochastic variations. We show that the embedding space obtained from the transformer encoder is semantically meaningful and linear. This enables the manipulation of high-level attributes, by discovering their linear direction of change in the semantic embedding space and moving the embedding along said direction. All code and data is made publicly available.}, } @article{bilewicz_emotional_nodate, title = {The emotional drivers of hate speech: {Unpacking} the central role of contempt in derogatory communication}, volume = {0}, issn = {1545-6870}, shorttitle = {The emotional drivers of hate speech}, url = {https://doi.org/10.1080/15456870.2025.2525790}, doi = {10.1080/15456870.2025.2525790}, abstract = {Derogatory communication about discriminated groups is commonly attributed to hate, but the emotional mechanism of such language remains under-explored. Three studies (S1, N = 682; S2, N = 43, \& S3, N = 150) examined how exposure to hate speech affects emotional responses toward target groups, which can then translate to further use of derogatory language. In Study 1, contempt, but also anger, acted as mediators between the exposure to and the use of hate speech. In Study 2, among participants exposed to high levels of hate speech, further exposure to derogatory language led to increased facial expression of contempt and joy, but to inhibited expression of sadness. In Study 3, participants exposed to hate speech expressed a higher level of contempt (but also anger and disgust) directed at victims of hate speech. Overall, we propose that contempt constitutes an affective mechanism responsible for the spread of harmful forms of intergroup communication.}, number = {0}, urldate = {2025-09-05}, year={2025}, journal = {Atlantic Journal of Communication}, author = {Bilewicz, Michał and Soral, Wiktor and Świderska, Aleksandra and Küster, Dennis and Winiewski, Mikołaj and Wypych, Michał}, note = {Publisher: Routledge \_eprint: https://doi.org/10.1080/15456870.2025.2525790}, pages = {1--19}, } @incollection{kuster_face_2024, address = {Cham}, title = {The {Face} {Behind} the {Mask}: {Thermography} of the {Face}}, isbn = {978-3-031-70064-4}, shorttitle = {The {Face} {Behind} the {Mask}}, url = {https://doi.org/10.1007/978-3-031-70064-4_12}, abstract = {What can facial thermography tell us about emotions? The notion that we can leverage measures of bodily responses to reveal something about our inner emotional experiences harks back to William James’ ground-breaking theory on the nature of emotions (James, 1884). At the same time, this quest has met with many criticisms along the way (see Cannon, 1927; Levenson, 2003). Deciphering the relationships between bodily signals and human emotions has fascinated generations of scholars (Levenson, 2003). The face, in particular, continues to attract a lot of interest (Kappas et al., 2013), as researchers hope that subtle and almost invisible changes in facial expressions might provide a key to unveiling someone’s genuine emotions. Where only a few specifically trained experts were previously believed to be able to see and interpret subtle cues of deception in facial muscle movements (Ekman et al., 1999; Frank \& Svetieva, 2015), recent technical advances in computational imaging (Nowara et al., 2022) and machine learning may be on the verge of changing this picture (Bian et al., 2024). Perhaps even more stunning, however, is the flexibility with which machine learning methods are beginning to integrate biosignals from different modalities and devices. For example, traditional RGB image data can now be fused with data from the invisible thermal spectrum (Chen et al., 2018; Wang et al., 2014, 2018), thereby allowing researchers to indeed look beneath the skin of facial movements. Could this mean that we may be close to the holy grail of reliably revealing the truth about someone’s emotions and thus revealing the face behind the mask?}, language = {en}, urldate = {2025-09-05}, booktitle = {Body {Language} {Communication}}, publisher = {Springer Nature Switzerland}, author = {Küster, Dennis}, editor = {Chadee, Derek and Kostić, Aleksandra}, year = {2024}, doi = {10.1007/978-3-031-70064-4_12}, pages = {285--313}, } @inproceedings{liu2025emg_auc, address = {Cham}, title = {{EMG}-Based Action Unit Recognition: {F}eature Engineering, Machine Learning, and Real-Time Classification}, isbn = {978-3-031-96899-0}, shorttitle = {{EMG}-Based Action Unit Recognition}, doi = {10.1007/978-3-031-96899-0_3}, abstract = {This article is an extended version of the work originally presented at the BIODEVICES 2024 conference, which exclusively focuses on utilizing fEMG as the primary method for action unit recognition (AUR). Within the framework of this study, we employ a proprietary dataset of facial electromyography (fEMG) sensor data, which contains synchronized video modality data with fEMG recordings and output labels corresponding to appropriate AUs, to predict a subset of action units. Abundant feature engineering practice and machine learning experiments are conducted to study fEMG-based AUR.}, booktitle = {Biomedical Engineering Systems and Technologies}, publisher = {Springer Nature Switzerland}, author = {Liu, Hui and Veldanda, Abhinav and Koschke, Rainer and Schultz, Tanja and Küster, Dennis}, year = {2025}, keywords = {Action units, Electromyography, EMG, Facial action coding system, Facial expression, fEMG, Machine learning, Pattern recognition, sEMG}, pages = {23--43}, doi = {10.1007/978-3-031-96899-0_3}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/LiuVeldandaKoschkeSchultzKuester_CCIS2025.pdf} } @inproceedings{ouyang2025muscle_synergy, address = {Cham}, title = {Muscle Synergy and Co-contraction Effects on Joystick Manipulation}, isbn = {978-3-031-96899-0}, doi = {10.1007/978-3-031-96899-0_16}, abstract = {Extracting muscle synergy from surface electromyographic (sEMG) signals has become a standard method for evaluating motor control strategies during exercise. While numerous studies have described the synergy of the upper extremity in various stretch and reach tasks, few have analyzed the relationship between task performance and muscle synergy. This study introduces an experimental device and analysis method for examining muscle coordination in joystick manipulation, specifically for pilots. In this study, eight healthy subjects performed joystick manipulation tasks involving isotonic exercises with three different load levels. EMG and acceleration data from ten muscles were recorded. The muscle synergy effect was extracted, and the correlation between muscle synergy similarity, manipulation performance, and interaction load was analyzed. The experimental data revealed that while manipulation performance varied under different loading conditions, there were no significant changes in the synergistic muscle structure. Significant correlations were found between the similarity of some synergistic muscle structures and manipulation performance. However, there was no strong correlation between individual action performance and the average similarity of their muscle synergy. The analysis indicated a fixed muscle synergy pattern during rocker manipulation, which remained independent of the rocker load level. A negative correlation was observed between muscle synergy similarity and manipulation performance, as well as between muscle co-contraction index and manipulation performance. These findings contribute to improving the ergonomics of the flight stick and suggest targeted muscle training methods to enhance the precision of flight maneuvers.}, booktitle = {Biomedical Engineering Systems and Technologies}, publisher = {Springer Nature Switzerland}, author = {Chuanyun Ouyang and Liming Cai and Shuhao Yan and Tianxiang Zhang and Jun Zhu and Li Chen and Hui Liu}, year = {2025}, keywords = {Muscle synergy extraction, Muscle synergy similarity, Accuracy, Manipulate, Electromyography, EMG, sEMG}, pages = {270--292}, doi = {10.1007/978-3-031-96899-0_16}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/OuyangCaiYanZhangZhuChenLiu__CCIS2025.pdf} } @book{CCIS2025, title = {Biomedical Engineering Systems and Technologies}, subtitle = {17th International Joint Conference, BIOSTEC 2024, Rome, Italy, February 21–23, 2024, Revised Selected Papers}, author = {Zhi-Rui Xie and Yang Chen and Yu-Ying Hou and Bei-Bei Lin and Long-Teng Xie and Yao-Gen Shu and Shival Indermun and Hui Liu and Abhinav Veldanda and Rainer Koschke and Tanja Schultz and Dennis Küster and et. al.}, editor = {Maria Pedro Guarino, Kazuhiro Hotta, Malik Yousef, Hui Liu, Giovanni Saggio, Hannes Schlieter, Ana Fred and Hugo Gamboa}, publisher = {Springer Cham}, isbn = {978-3-031-96898-3}, issn = {1865-0929}, year = {2025}, month = {aug}, doi = {10.1007/978-3-031-96899-0}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/Biomedical_Engineering_Systems_and_Technologies_CCIS2025.pdf} } @inproceedings{scheck25_interspeech, title = {{DiffMV-ETS: Diffusion-based Multi-Voice Electromyography-to-Speech Conversion using Speaker-Independent Speech Training Targets}}, author = {Kevin Scheck and Tom Dombeck and Zhao Ren and Peter Wu and Michael Wand and Tanja Schultz}, year = {2025}, booktitle = {{Interspeech 2025}}, pages = {5573--5577}, doi = {10.21437/Interspeech.2025-1914}, issn = {2958-1796}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/Scheck2025-DiffMV-ETS.pdf} } @article{chiossi2025designing, title={Designing and evaluating an adaptive virtual reality system using eeg frequencies to balance internal and external attention states}, author={Chiossi, Francesco and Ou, Changkun and Gerhardt, Carolina and Putze, Felix and Mayer, Sven}, journal={International Journal of Human-Computer Studies}, volume={196}, pages={103433}, year={2025}, publisher={Elsevier}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/designing_evaluating_2025.pdf} } @inproceedings{chiossi2024detecting, title={Detecting internal and external attention in virtual reality: A comparative analysis of EEG classification methods}, author={Chiossi, Francesco and Ou, Changkun and Putze, Felix and Mayer, Sven}, booktitle={Proceedings of the International Conference on Mobile and Ubiquitous Multimedia}, pages={381--395}, year={2024}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/detecting_internal_external_2024.pdf} } @article{schultz2024lablinking, title={LabLinking: theory, framework, and solutions of connecting laboratories for distributed human experiments}, author={Schultz, Tanja and Putze, Felix and Reisenhofer, Rafael and Fehr, Thorsten and Meier, Moritz and Mason, Celeste and Ahrens, Florian}, journal={Discover Applied Sciences}, volume={6}, number={9}, pages={448}, year={2024}, publisher={Springer}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/lablinking_2024.pdf} } @article{bredereke_modular_2025, title = {A {Modular} {Pipeline} for {3D} {Object} {Tracking} {Using} {RGB} {Cameras}}, volume = {4322}, url = {https://scholar.google.com/citations?view_op=view_citation\&hl=en\&user=CupDmmcAAAAJ\&cstart=500\&pagesize=100\&citation_for_view=CupDmmcAAAAJ:NXYAu82O0W8C}, journal = {arXiv preprint arXiv:2503.}, author = {Bredereke, L. and Hartmann, Y. and Schultz, T.}, year = {2025}, note = {Type: Preprint}, annote = {Query date: 2026-02-09 15:30:27}, } @incollection{steinert_ai_2025, address = {Cham}, title = {{AI} {Meets} {Digital} {Public} {Health}}, isbn = {978-3-031-90154-6}, url = {https://doi.org/10.1007/978-3-031-90154-6_27}, doi = {10.1007/978-3-031-90154-6_27}, abstract = {While Artificial Intelligence (AI) has already brought disruptive changes to public health (PH), the effective deployment of AI technologies requires an interdisciplinary approach to address ethical, legal, societal, and security challenges. This chapter aims to provide PH experts with a common understanding of AI and the terminology to facilitate interdisciplinary collaborations. Furthermore, this chapter highlights the potential of AI for the field of PH, particularly the emerging field of digital public health (DiPH). For this purpose, the chapter briefly introduces the concepts of AI and its applications through actual examples from DiPH. Thereafter, a critical perspective is presented on ensuring AI deployment in DiPH while adhering to ethical regulations. To demonstrate how an AI intervention can be responsibly implemented, a tablet-based activation system for people with dementia is used as an example.}, language = {en}, urldate = {2026-02-10}, booktitle = {Digital {Public} {Health}: {Interdisciplinary} {Perspectives}}, publisher = {Springer Nature Switzerland}, author = {Steinert, Lars and Diethei, Daniel and Hoel, Viktoria and Hahn, Horst K. and Wolf-Ostermann, Karin and Wright, Marvin N. and Schultz, Tanja}, editor = {Zeeb, Hajo and Maaß, Laura and Schultz, Tanja and Haug, Ulrike and Pigeot, Iris and Schüz, Benjamin}, year = {2025}, keywords = {AI applications, Artificial Intelligence, Cognitive systems, Computer science, Digital public health, Ethical design, Human-Computer Interaction, Machine Learning, Recommender systems, Technical assistance systems}, pages = {513--535}, file = {Full Text PDF:C\:\\Users\\kuest\\Zotero\\storage\\RXGTNL8F\\Steinert et al. - 2025 - AI Meets Digital Public Health.pdf:application/pdf}, } @article{odone_artificial_2025, title = {Artificial intelligence and infectious diseases: an evidence-driven conceptual framework for research, public health, and clinical practice}, issn = {1473-3099}, shorttitle = {Artificial intelligence and infectious diseases}, url = {https://www.sciencedirect.com/science/article/pii/S1473309925004128}, doi = {10.1016/S1473-3099(25)00412-8}, abstract = {As artificial intelligence (AI) is projected to radically shape health care, its role in infectious disease prevention and management is drawing attention. AI offers promising opportunities to help tackle infectious disease threats and improve clinical management, outbreak detection, and infection control. As part of a dedicated Series on AI and infectious diseases, this paper sets the scene by proposing a conceptual framework that, building upon available AI models and data sources related to pathogens, human hosts, and the environment, comprehensively identifies selected domains where AI can be applied across infectious disease research, public health, and clinical practice. Building on this foundation, the two companion papers in the Series follow with an in-depth exploration of AI applications in diagnostics and antimicrobial resistance. We provide an overview of current and future applications of AI in infectious disease prevention and management, exploring the broad potential, available experimental evidence, real-life implementation examples, and technical normative, ethical, and policy barriers.}, urldate = {2026-02-10}, journal = {The Lancet Infectious Diseases}, author = {Odone, Anna and Barbati, Chiara and Amadasi, Silvia and Schultz, Tanja and Resnik, David B}, month = sep, year = {2025}, file = {ScienceDirect Snapshot:C\:\\Users\\kuest\\Zotero\\storage\\A54LZM3S\\S1473309925004128.html:text/html}, } @inproceedings{pahuja_atgnet_2025, title = {{ATGnet}: {Adaptive} {Temporal} {Graph} {Network} for {EEG}-enabled {Sound} {Source} {Tracking} in {Cocktail} {Party} {Scenarios}}, issn = {2379-190X}, shorttitle = {{ATGnet}}, url = {https://ieeexplore.ieee.org/abstract/document/10890424}, doi = {10.1109/ICASSP49660.2025.10890424}, abstract = {Decoding selective auditory attention from electroencephalography (EEG) signals has gained considerable interest. However, few studies have looked into tracking the dynamic trajectory of moving sound source in complex auditory environments, e.g. with multiple moving speakers. We propose a novel model, namely Adaptive Temporal Graph Network (ATGnet), to continuously track the sound source trajectory using spatial-temporal EEG representations. ATGnet incorporates an adaptive graph topology to extract spatial features, and a graph-convolutional long short-term memory (GC-LSTM) network to capture spatial-temporal dependency. We evaluated ATGnet by performing within-subject leave-one-trial-out cross-validation on EEG signals from 10 participants. Experiment results indicate that ATGnet effectively overcomes the variation of signals across trials and subjects. They further confirm that ATGnet robustly tracks both attended and unattended sound sources, and significantly outperforms traditional methods. ATGnet offers a promising solution to continuous sound source tracking in dynamic conditions, with potential applications in neuro-steered hearing devices.}, urldate = {2026-02-10}, booktitle = {{ICASSP} 2025 - 2025 {IEEE} {International} {Conference} on {Acoustics}, {Speech} and {Signal} {Processing} ({ICASSP})}, author = {Pahuja, Saurav and Ivucic, Gabriel and Cai, Siqi and De Silva, Dashanka and Schultz, Tanja and Li, Haizhou}, month = apr, year = {2025}, note = {ISSN: 2379-190X}, keywords = {Adaptation models, Adaptive systems, Auditory attention decoding, Brain modeling, Decoding, EEG, Electroencephalography, Feature extraction, Graph neural networks, Sound source tracking, Speech processing, Topology, Tracking, Trajectory, Trajectory reconstruction}, pages = {1--5}, file = {Full Text PDF:C\:\\Users\\kuest\\Zotero\\storage\\TKSP9R32\\Pahuja et al. - 2025 - ATGnet Adaptive Temporal Graph Network for EEG-enabled Sound Source Tracking in Cocktail Party Scen.pdf:application/pdf}, } @inproceedings{paul_automated_2025, title = {Automated {Assessment} {Tests} with {Depth} {Sensors} in {Older} {Adults}}, issn = {2694-0604}, url = {https://ieeexplore.ieee.org/abstract/document/11252802}, doi = {10.1109/EMBC58623.2025.11252802}, abstract = {Mobility assessments are essential for understanding frailty in older adults, as they indicate mobility conditions and the likelihood of falls. Continuous assessments using automated systems allow us to detect mobility changes early and to improve mobility before severe events occur. In this study, we aim to automate the assessment tests using depth images. We present an automated Short Physical Performance Battery (SPPB) test using a depth sensor that captures older adults performing the SPPB test. Additionally, we discuss an automated Timed-Up-and-Go (TUG) test. We propose a method that identifies activities based on skeleton joints extracted from depth images and subsequently predicts the corresponding SPPB test scores. These scores serve as criteria for classifying older adults into high-risk, borderline, or not-at-risk for frailty. To achieve this, we collected 70 minutes of assessment data from 17 older outpatients at a long-term care facility. The proposed automated SPPB system achieved 98\% MSE accuracy in predicting SPPB scores. Furthermore, automated prediction of TUG timing using an LSTM model achieved an MSE accuracy of 94\%.Clinical relevance— The Short Physical Performance Battery (SPPB) and Timed-up-and-go (TUG) assessment scores are valuable clinical tools that help physicians evaluate a person’s frailty level. These assessments can guide the implementation of targeted physiotherapy and mobility-enhancing training programs. Since motor function is a key indicator of various medical conditions, physicians can use the assessment test values to determine the necessity of further diagnostic tests, facilitating the early detection and management of underlying diseases.}, urldate = {2026-02-10}, booktitle = {2025 47th {Annual} {International} {Conference} of the {IEEE} {Engineering} in {Medicine} and {Biology} {Society} ({EMBC})}, author = {Paul, Rinu Elizabeth and Kock, Pantea and Deichsel, Lucas and Hartmann, Yale and Schultz, Tanja}, month = jul, year = {2025}, note = {ISSN: 2694-0604}, keywords = {Accuracy, Batteries, Diseases, Long short term memory, Motors, Older adults, Predictive models, Skeleton, Timing, Training}, pages = {1--7}, file = {Full Text PDF:C\:\\Users\\kuest\\Zotero\\storage\\UWKKAHZM\\Paul et al. - 2025 - Automated Assessment Tests with Depth Sensors in Older Adults.pdf:application/pdf}, } @misc{ren_introduction_2025, title = {An {Introduction} to {Silent} {Paralinguistics}}, url = {http://arxiv.org/abs/2508.18127}, doi = {10.48550/arXiv.2508.18127}, abstract = {The ability to speak is an inherent part of human nature and fundamental to our existence as a social species. Unfortunately, this ability can be restricted in certain situations, such as for individuals who have lost their voice or in environments where speaking aloud is unsuitable. Additionally, some people may prefer not to speak audibly due to privacy concerns. For such cases, silent speech interfaces have been proposed, which focus on processing biosignals corresponding to silently produced speech. These interfaces enable synthesis of audible speech from biosignals that are produced when speaking silently and recognition aka decoding of biosignals into text that corresponds to the silently produced speech. While recognition and synthesis of silent speech has been a prominent focus in many research studies, there is a significant gap in deriving paralinguistic information such as affective states from silent speech. To fill this gap, we propose Silent Paralinguistics, aiming to predict paralinguistic information from silent speech and ultimately integrate it into the reconstructed audible voice for natural communication. This survey provides a comprehensive look at methods, research strategies, and objectives within the emerging field of silent paralinguistics.}, urldate = {2026-02-10}, publisher = {arXiv}, author = {Ren, Zhao and Pistrosch, Simon and Coşkun, Buket and Scheck, Kevin and Batliner, Anton and Schuller, Björn W. and Schultz, Tanja}, month = aug, year = {2025}, note = {arXiv:2508.18127 [cs]}, keywords = {Computer Science - Human-Computer Interaction}, annote = {Comment: 21 pages}, file = {Preprint PDF:C\:\\Users\\kuest\\Zotero\\storage\\4E49UIAP\\Ren et al. - 2025 - An Introduction to Silent Paralinguistics.pdf:application/pdf;Snapshot:C\:\\Users\\kuest\\Zotero\\storage\\PPSML6Z5\\2508.html:text/html}, } @inproceedings{chang_breaking_2025, title = {Breaking {Resource} {Barriers} in {Speech} {Emotion} {Recognition} via {Data} {Distillation}}, issn = {2308-457X}, url = {http://pure.bit.edu.cn/zh/publications/breaking-resource-barriers-in-speech-emotion-recognition-via-data/}, doi = {10.21437/Interspeech.2025-2778}, language = {英语}, urldate = {2026-02-10}, booktitle = {Proceedings of the {Annual} {Conference} of the {International} {Speech} {Communication} {Association}, {INTERSPEECH}}, publisher = {International Speech Communication Association}, author = {Chang, Yi and Ren, Zhao and Zhao, Zhonghao and Nguyen, Thanh Tam and Qian, Kun and Schultz, Tanja and Schuller, Björn W.}, year = {2025}, pages = {141--145}, file = {Snapshot:C\:\\Users\\kuest\\Zotero\\storage\\P9QKGGNB\\breaking-resource-barriers-in-speech-emotion-recognition-via-data.html:text/html}, } @misc{wald_breathe_2025, title = {Breathe with {Me}: {Synchronizing} {Biosignals} for {User} {Embodiment} in {Robots}}, shorttitle = {Breathe with {Me}}, url = {http://arxiv.org/abs/2512.14952}, doi = {10.48550/arXiv.2512.14952}, abstract = {Embodiment of users within robotic systems has been explored in human-robot interaction, most often in telepresence and teleoperation. In these applications, synchronized visuomotor feedback can evoke a sense of body ownership and agency, contributing to the experience of embodiment. We extend this work by employing embreathment, the representation of the user's own breath in real time, as a means for enhancing user embodiment experience in robots. In a within-subjects experiment, participants controlled a robotic arm, while its movements were either synchronized or non-synchronized with their own breath. Synchrony was shown to significantly increase body ownership, and was preferred by most participants. We propose the representation of physiological signals as a novel interoceptive pathway for human-robot interaction, and discuss implications for telepresence, prosthetics, collaboration with robots, and shared autonomy.}, urldate = {2026-02-10}, publisher = {arXiv}, author = {Wald, Iddo Yehoshua and Maimon, Amber and Zhang, Shiyao and Küster, Dennis and Porzel, Robert and Schultz, Tanja and Malaka, Rainer}, month = dec, year = {2025}, note = {arXiv:2512.14952 [cs]}, keywords = {Computer Science - Human-Computer Interaction, Computer Science - Robotics}, annote = {Comment: Accepted to appear in the ACM/IEEE International Conference on Human-Robot Interaction (HRI '26), Edinburgh, United Kingdom. Iddo Yehoshua Wald and Amber Maimon contributed equally}, file = {Preprint PDF:C\:\\Users\\kuest\\Zotero\\storage\\RL6ZF9YH\\Wald et al. - 2025 - Breathe with Me Synchronizing Biosignals for User Embodiment in Robots.pdf:application/pdf;Snapshot:C\:\\Users\\kuest\\Zotero\\storage\\UKBYX6QL\\2512.html:text/html}, } @inproceedings{de_silva_ca-neurospex_2025, title = {{CA}-{NeuroSpex}: {Context}-{Informed} {Autoregressive} {Neuro}-{Guided} {Speaker} {Extraction}}, issn = {2694-0604}, shorttitle = {{CA}-{NeuroSpex}}, url = {https://ieeexplore.ieee.org/abstract/document/11251577}, doi = {10.1109/EMBC58623.2025.11251577}, abstract = {Neuro-guided target speaker extraction (TSE) leverages neural responses to guide the extraction of attended speech from competing sources, mirroring the brain’s ability to navigate multi-speaker environments. However, traditional neuro-guided methods overlook the importance of temporal context. To bridge this gap, we introduce CA-NeuroSpex, a novel context-informed end-to-end TSE framework. It harnesses autoregressive feedback to integrate previously extracted speech as a secondary reference cue via a specialized speech-context encoder. By dynamically fusing this contextual cue with the neural cue, CA-NeuroSpex bolsters extraction performance in a causal decoder setup. Our key contributions include a speech-context encoder for overlapping speech integration, a teacher-forced autoregressive training paradigm, and a gating mechanism for cue fusion. Our results demonstrate the effectiveness of combining dynamic contextual and neural information for robust speaker extraction.}, urldate = {2026-02-10}, booktitle = {2025 47th {Annual} {International} {Conference} of the {IEEE} {Engineering} in {Medicine} and {Biology} {Society} ({EMBC})}, author = {De Silva, Dashanka and Cai, Siqi and Pahuja, Saurav and Schultz, Tanja and Li, Haizhou}, month = jul, year = {2025}, note = {ISSN: 2694-0604}, keywords = {autoregressive feedback, Brain modeling, Bridges, Context modeling, Data mining, Decoding, EEG, Electroencephalography, Engineering in medicine and biology, Navigation, selective auditory attention, speech, Speech enhancement, target speaker extraction, Training}, pages = {1--7}, file = {Full Text PDF:C\:\\Users\\kuest\\Zotero\\storage\\AFM5EEXQ\\De Silva et al. - 2025 - CA-NeuroSpex Context-Informed Autoregressive Neuro-Guided Speaker Extraction.pdf:application/pdf}, } @incollection{zeeb_digital_2025, address = {Cham}, title = {Digital {Public} {Health}: {An} {Outlook}}, isbn = {978-3-031-90154-6}, shorttitle = {Digital {Public} {Health}}, url = {https://doi.org/10.1007/978-3-031-90154-6_31}, doi = {10.1007/978-3-031-90154-6_31}, abstract = {This chapter provides a summary overview and an outlook towards different pathways which the future of digital public health may take. We discuss three somewhat distinct potential scenarios, including a dystopian view, a slow transformation scenario and comprehensively digitalized public health landscape, while also summarizing core insights from different chapters of this book.}, language = {en}, urldate = {2026-02-10}, booktitle = {Digital {Public} {Health}: {Interdisciplinary} {Perspectives}}, publisher = {Springer Nature Switzerland}, author = {Zeeb, Hajo and Maaß, Laura and Haug, Ulrike and Pigeot, Iris and Schultz, Tanja and Schüz, Benjamin}, editor = {Zeeb, Hajo and Maaß, Laura and Schultz, Tanja and Haug, Ulrike and Pigeot, Iris and Schüz, Benjamin}, year = {2025}, keywords = {Digital public health, Empowerment, Equity, ethics, Future scenarios}, pages = {613--618}, file = {Full Text PDF:C\:\\Users\\kuest\\Zotero\\storage\\PGN6Z43B\\Zeeb et al. - 2025 - Digital Public Health An Outlook.pdf:application/pdf}, } @book{zeeb_digital_2025-1, address = {Cham}, series = {Springer {Series} on {Epidemiology} and {Public} {Health}}, title = {Digital {Public} {Health}: {Interdisciplinary} {Perspectives}}, copyright = {https://creativecommons.org/licenses/by/4.0}, isbn = {978-3-031-90153-9 978-3-031-90154-6}, shorttitle = {Digital {Public} {Health}}, url = {https://link.springer.com/10.1007/978-3-031-90154-6}, doi = {10.1007/978-3-031-90154-6}, language = {en}, urldate = {2026-02-10}, publisher = {Springer Nature Switzerland}, editor = {Zeeb, Hajo and Maaß, Laura and Schultz, Tanja and Haug, Ulrike and Pigeot, Iris and Schüz, Benjamin}, year = {2025}, keywords = {Artificial Intelligence, data protection, Digital Divide, Digitalization, Evaluation, Global Digital Public Health, Interdisciplinarity, Literacy, Open Access, Public Health Operations, Social Media, Surveillance and Monitoring}, file = {Full Text PDF:C\:\\Users\\kuest\\Zotero\\storage\\7TMDX8LB\\Zeeb et al. - 2025 - Digital Public Health Interdisciplinary Perspectives.pdf:application/pdf}, } @misc{rammohan_easelan_2025, title = {{EASELAN}: {An} {Open}-{Source} {Framework} for {Multimodal} {Biosignal} {Annotation} and {Data} {Management}}, shorttitle = {{EASELAN}}, url = {http://arxiv.org/abs/2510.15767}, doi = {10.48550/arXiv.2510.15767}, abstract = {Recent advancements in machine learning and adaptive cognitive systems are driving a growing demand for large and richly annotated multimodal data. A prominent example of this trend are fusion models, which increasingly incorporate multiple biosignals in addition to traditional audiovisual channels. This paper introduces the EASELAN annotation framework to improve annotation workflows designed to address the resulting rising complexity of multimodal and biosignals datasets. It builds on the robust ELAN tool by adding new components tailored to support all stages of the annotation pipeline: From streamlining the preparation of annotation files to setting up additional channels, integrated version control with GitHub, and simplified post-processing. EASELAN delivers a seamless workflow designed to integrate biosignals and facilitate rich annotations to be readily exported for further analyses and machine learning-supported model training. The EASELAN framework is successfully applied to a high-dimensional biosignals collection initiative on human everyday activities (here, table setting) for cognitive robots within the DFG-funded Collaborative Research Center 1320 Everyday Activity Science and Engineering (EASE). In this paper we discuss the opportunities, limitations, and lessons learned when using EASELAN for this initiative. To foster research on biosignal collection, annotation, and processing, the code of EASELAN is publicly available(https://github.com/cognitive-systems-lab/easelan), along with the EASELAN-supported fully annotated Table Setting Database.}, urldate = {2026-02-10}, publisher = {arXiv}, author = {Rammohan, Rathi Adarshi and Meier, Moritz and Küster, Dennis and Schultz, Tanja}, month = oct, year = {2025}, note = {arXiv:2510.15767 [cs]}, keywords = {Computer Science - Software Engineering}, file = {Preprint PDF:C\:\\Users\\kuest\\Zotero\\storage\\5MKVPEH8\\Rammohan et al. - 2025 - EASELAN An Open-Source Framework for Multimodal Biosignal Annotation and Data Management.pdf:application/pdf;Snapshot:C\:\\Users\\kuest\\Zotero\\storage\\4LJISSI5\\2510.html:text/html}, } @inproceedings{ren_end--end_2025, title = {End-to-end {Acoustic}-linguistic {Emotion} and {Intent} {Recognition} {Enhanced} by {Semi}-supervised {Learning}}, issn = {2694-0604}, url = {https://ieeexplore.ieee.org/abstract/document/11254936/authors}, doi = {10.1109/EMBC58623.2025.11254936}, abstract = {Emotion and intent recognition from speech is essential and has been widely investigated in human-computer interaction. The rapid development of social media platforms, chatbots, and other technologies has led to a large volume of speech data streaming from users. Nevertheless, annotating such data manually is expensive, making it challenging to train machine learning models for recognition purposes. To this end, we propose applying semi-supervised learning to incorporate a large scale of unlabelled data alongside a relatively smaller set of labelled data. We train end-to-end acoustic and linguistic models, each employing multi-task learning for emotion and intent recognition. Two semi-supervised learning approaches, including fix-match learning and full-match learning, are compared. The experimental results demonstrate that the semi-supervised learning approaches improve model performance in speech emotion and intent recognition from both acoustic and text data. The late fusion of the best models outperforms the acoustic and text baselines by joint recognition balance metrics of 12.3 \% and 10.4 \%, respectively.}, urldate = {2026-02-10}, booktitle = {2025 47th {Annual} {International} {Conference} of the {IEEE} {Engineering} in {Medicine} and {Biology} {Society} ({EMBC})}, author = {Ren, Zhao and Rammohan, Rathi Adarshi and Scheck, Kevin and Li, Sheng and Schultz, Tanja}, month = jul, year = {2025}, note = {ISSN: 2694-0604}, keywords = {Acoustics, Data models, Intent recognition, Machine learning, Measurement, Multitasking, Semisupervised learning, Social networking (online), Speech recognition, Text recognition}, pages = {1--5}, file = {Full Text PDF:C\:\\Users\\kuest\\Zotero\\storage\\BUYWJDXL\\Ren et al. - 2025 - End-to-end Acoustic-linguistic Emotion and Intent Recognition Enhanced by Semi-supervised Learning.pdf:application/pdf}, } @inproceedings{brause_explaining_2025, title = {Explaining {Multimodal} {Features} for {Screening} of {Cognitive} {Impairment} {Using} {Shapley} {Values}}, issn = {2694-0604}, url = {https://ieeexplore.ieee.org/abstract/document/11251859}, doi = {10.1109/EMBC58623.2025.11251859}, abstract = {Many approaches for Alzheimer’s disease screening focus on either medical imaging or speech as modalities. However, our previous work shows that unimodal models utilizing features from either conversational speech or structural brain imaging are outperformed by models leveraging features of both modalities simultaneously. Herein, we use XAI techniques based on Shapley values to investigate which features are most influential for the multimodal models’ decisions on the fusion and the input level in both state and predictive screening. We analyze individual patients using Shapley-based methods like SHAP, GradSHAP and DeepSHAP, and derive global insights for the most important features by aggregating these local techniques. We find that the models benefit from using both modalities, although volumetric features derived from brain imaging contribute more towards the classification results than acoustic and linguistic features derived from speech in both screening types.Clinical Relevance—Applying explainability methods to multimodal machine learning models enhances reliability and robustness of trained models, can support clinicians in interpreting the deployed model’s decision, and may guide selection of the most important screening modalities in the future.}, urldate = {2026-02-10}, booktitle = {2025 47th {Annual} {International} {Conference} of the {IEEE} {Engineering} in {Medicine} and {Biology} {Society} ({EMBC})}, author = {Brauße, Elisa and Koenen, Niklas and Wright, Marvin N. and Schultz, Tanja}, month = jul, year = {2025}, note = {ISSN: 2694-0604}, keywords = {Alzheimer's disease, Biological system modeling, Biomedical imaging, Brain modeling, Linguistics, Machine learning, Neuroimaging, Predictive models, Robustness, Speech enhancement}, pages = {1--6}, file = {Full Text PDF:C\:\\Users\\kuest\\Zotero\\storage\\THAK277Z\\Brauße et al. - 2025 - Explaining Multimodal Features for Screening of Cognitive Impairment Using Shapley Values.pdf:application/pdf}, } @article{hartmann_gait_2025, title = {Gait parameter estimation from a single depth sensor}, volume = {4}, issn = {2772-3577}, url = {https://doi.org/10.1177/27723577251320237}, doi = {10.1177/27723577251320237}, abstract = {In this article, we present our collected dataset with hardware-synchronized motion capture and depth sensors of a freely moving subject, our estimation of human pose, stride length, step length, and step length classification using deep learning, classical machine learning, and established algorithms. Our results on the 157,825-frame dataset show that pose estimation can be done with up to 85.91\% of correct keypoints and as low as 8.86 cm mean per key point error with 2–3 cm of that error attributed to camera imprecision due to the 2–4 m distance. The stride estimation achieves up to 99.58\% step percent and 100.39\% distance ratio. The center of mass and foot distance based step length estimations show very similar step counts with 1380 and 1396, respectively, but differ in the total distance traveled at 58 m. The step length classification works well with an equal class recognition spread at an overall 80\% accuracy. The core contributions of this work are the developed pose estimation models and the evaluation of all machine learning models and algorithms, the pipeline and evaluation scheme for every step from depth sequences to stride and step length estimation in a scenario of a freely moving subject, and the in-depth analysis tying the signals, algorithms, models, and gait phases together and highlighting the importance of different joint sets for step length classification.}, language = {EN}, number = {1}, urldate = {2026-02-10}, journal = {Journal of Smart Cities and Society}, publisher = {SAGE Publications}, author = {Hartmann, Yale and Paul, Rinu Elizabeth and Klöckner, Jonah and Deichsel, Lucas and Schultz, Tanja}, month = feb, year = {2025}, pages = {35--61}, file = {SAGE PDF Full Text:C\:\\Users\\kuest\\Zotero\\storage\\NJDRFAKB\\Hartmann et al. - 2025 - Gait parameter estimation from a single depth sensor.pdf:application/pdf}, } @inproceedings{ivucic_geo-gcn_2025, title = {Geo-{GCN}: {Geometric}-{Graphical} {Convolutional} {Network} for {EEG}-based {Auditory} {Attention} {Detection}}, issn = {2694-0604}, shorttitle = {Geo-{GCN}}, url = {https://ieeexplore.ieee.org/abstract/document/11251825}, doi = {10.1109/EMBC58623.2025.11251825}, abstract = {Auditory attention detection (AAD) reveals listeners’ attention to a speech stimulus based on their elicited electroencephalography (EEG) signals. We propose a geometric graph convolutional network (Geo-GCN) that uses the physical layout of EEG sensors to construct a distance-based adjacency matrix. This enables Geo-GCN to perform more biologically informed feature learning than standard GCNs. Using data from participants with normal hearing (NH) and hearing-impaired (HI), our method outperforms traditional GCNs. Geo-GCN also demonstrates lower performance variability among participants. Analysis of separate NH and HI groups shows consistent gains over standard GCN, underlining the benefit of explicit modeling of scalp geometry. These findings highlight the potential of geometry-aware graph neural networks to improve EEG-based auditory attention detection, particularly in heterogeneous populations with varied hearing capabilities.}, urldate = {2026-02-10}, booktitle = {2025 47th {Annual} {International} {Conference} of the {IEEE} {Engineering} in {Medicine} and {Biology} {Society} ({EMBC})}, author = {Ivucic, Gabriel and Pahuja, Saurav and Li, Haizhou and Schultz, Tanja}, month = jul, year = {2025}, note = {ISSN: 2694-0604}, keywords = {Accuracy, Auditory system, Brain modeling, Deafness, Electroencephalography, Layout, Representation learning, Scalp, Sensors, Standards}, pages = {1--5}, file = {Full Text PDF:C\:\\Users\\kuest\\Zotero\\storage\\B4STNVHJ\\Ivucic et al. - 2025 - Geo-GCN Geometric-Graphical Convolutional Network for EEG-based Auditory Attention Detection.pdf:application/pdf}, } @inproceedings{rammohan_unveiling_2025, title = {Unveiling {Deep} {Speech} {Embeddings}: {Acoustic} {Insights} into {Hatespeech} {Detection}}, shorttitle = {Unveiling {Deep} {Speech} {Embeddings}}, url = {https://ieeexplore.ieee.org/abstract/document/11264306}, abstract = {Modern democratic societies face a growing challenge from hate speech, yet most research focuses on hatetext (written content) detection, overlooking valuable acoustic cues. To explore the potential of hatespeech (spoken content), this study focuses on hate detection using acoustic features and self-supervised speech embeddings in the HateMM dataset. We performed a layer-wise analysis of two fine-tuned speech models, Wav2Vec2.0 and HuBERT. A linear classifier yielded F1 scores of 0.8137 and 0.8106, demonstrating their effectiveness. To further interpret these models, canonical correlation analysis (CCA) was applied to measure the similarity between hand-crafted acoustic features and learned speech embeddings. Our findings highlight the role of energy-related features, embedded in layers of speech models, in distinguishing hatespeech from non-hatespeech.}, urldate = {2026-02-10}, booktitle = {Speech {Communication}; 16th {ITG} {Conference}}, author = {Rammohan, Rathi Adarshi and Ren, Zhao and Swiderska, Aleksandra and Kuester, Dennis and Schultz, Tanja}, month = sep, year = {2025}, pages = {16--20}, file = {Full Text PDF:C\:\\Users\\kuest\\Zotero\\storage\\NF56JH3Y\\Rammohan et al. - 2025 - Unveiling Deep Speech Embeddings Acoustic Insights into Hatespeech Detection.pdf:application/pdf}, } @article{wang_structural_2025, title = {Structural {Cerebral} {Correlates} of {Perplexity}: {Exploring} a {Linguistic} {Marker} in {Cognitive} {Aging}}, volume = {14}, copyright = {© 2025 The Author(s). PsyCh Journal published by Institute of Psychology, Chinese Academy of Sciences and John Wiley \& Sons Australia, Ltd.}, issn = {2046-0260}, shorttitle = {Structural {Cerebral} {Correlates} of {Perplexity}}, url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/pchj.70010}, doi = {10.1002/pchj.70010}, abstract = {Language changes are among the earliest indicators of cognitive decline in aging. Perplexity, a linguistic measure derived from information theory that quantifies speech predictability, has emerged as a potential marker for detecting early cognitive changes. However, its underlying neural substrates remain unclear. This study investigated the structural brain correlates of perplexity in 38 elderly participants (26 cognitively healthy, 12 with mild cognitive impairment) using magnetic resonance imaging (MRI). Perplexity was computed automatically from autobiographical interviews using single-word (1-g) and word-pair (2-g) models. Voxel-based morphometry analyses, adjusted for total intracranial volume, sex, and education, revealed distinct associations between perplexity measures and regional gray matter volume. Region-of-interest analyses confirmed significant positive correlations between 1-g perplexity and left middle temporal gyrus volume as well as between 2-g perplexity and left precuneus. These findings suggest that perplexity reflects both linguistic processing and autobiographical memory, as evidenced by its associations with language-relevant temporal regions and memory-related precuneus. This study provides initial insights into the neural basis of perplexity as a measure that captures both linguistic and content-related aspects of language production in cognitive aging.}, language = {en}, number = {3}, urldate = {2026-02-10}, journal = {PsyCh Journal}, author = {Wang, Xingsong and Herold, Christina J. and Frankenberg, Claudia and Ablimit, Ayimnisagul and Schultz, Tanja and Kong, Li and Schröder, Johannes}, year = {2025}, note = {\_eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/pchj.70010}, keywords = {cognitive aging, linguistic, mild cognitive impairment, MRI, perplexity}, pages = {407--416}, file = {Full Text PDF:C\:\\Users\\kuest\\Zotero\\storage\\SY95NIZL\\Wang et al. - 2025 - Structural Cerebral Correlates of Perplexity Exploring a Linguistic Marker in Cognitive Aging.pdf:application/pdf;Snapshot:C\:\\Users\\kuest\\Zotero\\storage\\KT42A7K8\\pchj.html:text/html}, } @article{cai_spiking_2026, title = {Spiking neural networks for {EEG} signal analysis: {From} theory to practice}, volume = {194}, issn = {0893-6080}, shorttitle = {Spiking neural networks for {EEG} signal analysis}, url = {https://www.sciencedirect.com/science/article/pii/S089360802501007X}, doi = {10.1016/j.neunet.2025.108127}, abstract = {The intricate and efficient information processing of the human brain, driven by spiking neural interactions, has led to the development of spiking neural networks (SNNs) as a cutting-edge neural network paradigm. Unlike traditional artificial neural networks (ANNs) that use continuous values, SNNs emulate the brain’s spiking mechanisms, offering enhanced temporal information processing and computational efficiency. This review addresses the critical gap between theoretical advancements and practical applications of SNNs in EEG signal analysis. We provide a comprehensive examination of recent SNN methodologies and their application to EEG signals, highlighting their potential benefits over conventional deep learning approaches. The review encompasses foundational knowledge of SNNs, detailed implementation strategies for EEG analysis, and challenges inherent to SNN-based methods. Practical guidance is provided through step-by-step instructions and accessible code available on GitHub, aimed at facilitating researchers’ adoption of these techniques. Additionally, we explore emerging trends and future research directions, emphasizing the potential of SNNs to advance brain-computer interfaces and neurofeedback systems. This paper serves as a valuable resource for bridging the gap between theoretical developments in SNNs and their practical implementation in EEG signal analysis.}, urldate = {2026-02-10}, journal = {Neural Networks}, author = {Cai, Siqi and Lin, Zheyuan and Liu, Xiaoli and Wei, Wenjie and Wang, Shuai and Zhang, Malu and Schultz, Tanja and Li, Haizhou}, month = feb, year = {2026}, keywords = {Brain-computer interface, EEG signals, Spiking neural network}, pages = {108127}, file = {ScienceDirect Full Text PDF:C\:\\Users\\kuest\\Zotero\\storage\\9EQ36TW9\\Cai et al. - 2026 - Spiking neural networks for EEG signal analysis From theory to practice.pdf:application/pdf;ScienceDirect Snapshot:C\:\\Users\\kuest\\Zotero\\storage\\93GH4VF3\\S089360802501007X.html:text/html}, } @inproceedings{manghat_shabdh_2025, title = {Shabdh: {A} multi lingual zero-shot voice cloning approach with speaker disentanglement}, issn = {2379-190X}, shorttitle = {Shabdh}, url = {https://ieeexplore.ieee.org/abstract/document/10890203}, doi = {10.1109/ICASSP49660.2025.10890203}, abstract = {This paper presents a zero-shot voice cloning system leveraging the DIS-Vector framework, which disentangles and encodes key speech features: content, pitch, timbre, and rhythm. Using the YourTTS architecture, the system synthesizes high-quality speech with precise control over both speaker identity and speech characteristics. The approach integrates multilingual data from the LIMMITS-25 dataset. The system employs neural codec TTS and clustering techniques for efficient and personalized speech synthesis. By utilizing DIS-Vector embeddings, the system enables zero-shot voice cloning, allowing the synthesis of speech in the voice of any unseen speaker with high fidelity and adaptability across multiple languages.}, urldate = {2026-02-10}, booktitle = {{ICASSP} 2025 - 2025 {IEEE} {International} {Conference} on {Acoustics}, {Speech} and {Signal} {Processing} ({ICASSP})}, author = {Manghat, Sreeram and Manghat, Sreeja and Schultz, Tanja}, month = apr, year = {2025}, note = {ISSN: 2379-190X}, keywords = {Acoustics, Cloning, Codecs, few shot, low resource languages, Multilingual, Rhythm, Signal processing, speech embeddings, Speech enhancement, Speech synthesis, Systems architecture, Timbre, voice cloning, voice conversion, zero-shot}, pages = {1--2}, file = {Full Text PDF:C\:\\Users\\kuest\\Zotero\\storage\\ENTCYE6P\\Manghat et al. - 2025 - Shabdh A multi lingual zero-shot voice cloning approach with speaker disentanglement.pdf:application/pdf}, } @inproceedings{pahuja_xagnet_2025, title = {{XAGnet}: {Cross}-{Attention} {Graph} {Network} for {Detecting} {Auditory} {Attention} in {Ear}-{EEG} {Signals}}, issn = {2694-0604}, shorttitle = {{XAGnet}}, url = {https://ieeexplore.ieee.org/abstract/document/11252872}, doi = {10.1109/EMBC58623.2025.11252872}, abstract = {Auditory Attention Detection (AAD) is essential for developing advanced brain-computer interfaces including neuro-steered hearing technologies capable of functioning in complex auditory environments. In this study, we propose XAGnet, a novel method that leverages ear-centered EEG (ear-EEG) data to model both intra-ear and inter-ear neural dependencies for detection of auditory attention to one of the spatial locations. Specifically, Graph Convolutional Networks (GCNs) are applied separately to left and right ear-EEG signals to extract spatial features from each side for intra-ear interactions. A cross-attention mechanism is then introduced to model inter-ear interactions between the left and right ears. The attended features are combined for multi-class classification, with each class representing a speaker or a speaking location. We evaluate our method on a publicly available ear-EEG dataset, involving AAD tasks with four speakers. Experimental results demonstrate that XAGnet outperforms baseline models, highlighting the effectiveness of modeling both intra-ear and inter-ear dependencies in AAD tasks.}, urldate = {2026-02-10}, booktitle = {2025 47th {Annual} {International} {Conference} of the {IEEE} {Engineering} in {Medicine} and {Biology} {Society} ({EMBC})}, author = {Pahuja, Saurav and Ivucic, Gabriel and Cai, Siqi and De Silva, Dashanka and Li, Haizhou and Schultz, Tanja}, month = jul, year = {2025}, note = {ISSN: 2694-0604}, keywords = {Accuracy, Auditory attention detection, Auditory system, Brain modeling, Brain-computer interfaces, Cross-attention mechanism, Data models, Ear, Ear-EEG, Electroencephalography, Engineering in medicine and biology, Feature extraction, Graph convolutional networks}, pages = {1--6}, file = {Full Text PDF:C\:\\Users\\kuest\\Zotero\\storage\\AC3LQNZG\\Pahuja et al. - 2025 - XAGnet Cross-Attention Graph Network for Detecting Auditory Attention in Ear-EEG Signals.pdf:application/pdf}, } @inproceedings{van_apeldoorn_expressive_2025, address = {New York, NY, USA}, series = {{IVA} '25}, title = {Expressive {Agents} in {Psychology} {Research}: {A} {Study} on {Nuanced} {Emotional} {Signaling} with {Dynamic} {Tears}}, isbn = {979-8-4007-1508-2}, shorttitle = {Expressive {Agents} in {Psychology} {Research}}, url = {https://dl.acm.org/doi/10.1145/3717511.3749288}, doi = {10.1145/3717511.3749288}, abstract = {Virtual agents (VAs) are increasingly used in psychology, healthcare, and education, yet realistic representations of nuanced emotional signals like tears remain underexplored. We present a novel real-time system that simulates dynamic, physics-based tears in high-fidelity Metahuman avatars using Unreal Engine 5.5. Unlike traditional shader or animation tricks, our system produces lifelike crying effects through Niagara's skeletal mesh traversal, custom scratch modules, and real-time surface interaction. In a first empirical study (N=56), we compared static and dynamic crying avatars. Results showed that dynamic tears significantly enhanced perceived sadness and emotional contagion, without altering perceived authenticity. These findings suggest that flowing tears amplify social sadness signaling. Our demo will showcase the system's technical design, research methodology, and results. This work contributes to the development of emotionally expressive VAs. It bridges insights from psychology and computer graphics to advancing the study of nuanced human-agent emotional communication.}, urldate = {2026-02-10}, booktitle = {Proceedings of the 25th {ACM} {International} {Conference} on {Intelligent} {Virtual} {Agents}}, publisher = {Association for Computing Machinery}, author = {van Apeldoorn, Nick and Voskens, Niels and Küster, Dennis}, month = oct, year = {2025}, pages = {1--2}, file = {Full Text PDF:C\:\\Users\\kuest\\Zotero\\storage\\GRNHG2V8\\van Apeldoorn et al. - 2025 - Expressive Agents in Psychology Research A Study on Nuanced Emotional Signaling with Dynamic Tears.pdf:application/pdf}, } @article{jahanian-najafabadi_task_2025, title = {Task load affects tool embodiment during virtual tool-use in young and older adults}, volume = {6}, issn = {2673-4192}, url = {https://www.frontiersin.org/journals/virtual-reality/articles/10.3389/frvir.2025.1637212/full}, doi = {10.3389/frvir.2025.1637212}, abstract = {IntroductionPrior research revealed that after virtual tool use training, younger as compared to older adults, experienced a higher sense of tool-ownership over virtual tools associated with changes in sensorimotor representation (i.e., body schema). Moreover, higher agency ratings over the tool were independent of their performance levels and the extent to which the virtual tool was integrated into their arm representation. In contrast, older adults exhibited an increased sense of agency, which was strongly associated with improvements in virtual tool use performance. Regardless, no changes to their body schema, and no emergence of a sense of ownership were revealed in older adults.MethodsComparing data from a questionnaire and an analogue scale as two subjective measurements of embodiment during and after virtual tool-use training, we investigated whether this tool embodiment in both age groups could be predicted by task load assessed with the NASA TLX where participants rated their perceived task load related to the tool-use task in six dimensions (mental, physical, temporal, effort, performance and frustration). Data from 34 younger and 39 healthy older adults were analyzed.ResultsResults revealed that in younger adults, mental load led to increased ownership ratings over the virtual tool, and physical load negatively affected the sense of agency. Older adults showed weaker effects, with performance load being the only significant predictor of higher agency ratings. Further analyses of the analogue scale, which was embedded as an interactive probe in the experiment, provided novel fine-grained data on perceived sense of control during the training. Our results highlight robust age-related differences in tool-use performance, with younger adults consistently completing tasks more quickly than older adults. Sense of control, captured through the embedded analogue scale, significantly predicted faster performance, whereas ownership ratings did not contribute to timing performance. Agency ratings alone were not predictive, but their relationship with performance varied across age groups, suggesting that different mechanisms may underlie perceived agency in younger and older participants.DiscussionTaken together, these findings indicate that while age strongly influences tool-use efficiency, subjective experiences of control and agency also shape performance, underscoring the value of incorporating multiple measures of embodiment for a comprehensive understanding of virtual tool use.}, language = {English}, urldate = {2026-02-10}, journal = {Frontiers in Virtual Reality}, publisher = {Frontiers}, author = {Jahanian-Najafabadi, Amir and Küster, Dennis and Putze, Felix and Godde, Ben}, month = oct, year = {2025}, keywords = {agency, healthy aging, ownership, task load, tool-use, virtual embodiment, visuo-tactile feedback}, file = {Full Text PDF:C\:\\Users\\kuest\\Zotero\\storage\\QJ7F22VR\\Jahanian-Najafabadi et al. - 2025 - Task load affects tool embodiment during virtual tool-use in young and older adults.pdf:application/pdf}, } @article{hietanen_impact_2026, title = {The impact of eyes on attributions of agency and experience in humanoid robots}, volume = {137}, issn = {1053-8100}, url = {https://www.sciencedirect.com/science/article/pii/S1053810025001564}, doi = {10.1016/j.concog.2025.103963}, abstract = {Humans’ tendency to attribute mental states to robots positively correlates with the increasingly human-like appearance of the robots. As eyes have been suggested to be “the windows to the soul”, in the present study we investigated whether the presence or absence of facial features appearing as eyes in humanoid robots affects how perceivers attribute mental capacities of agency and experience to robots. We created images of highly realistic humanoid robots with full bodies and showed these robots either with the eyes or without the eyes. In Experiment 1, attribution of agency and experience was measured with self-evaluation questionnaires, whereas in Experiment 2, we used the Implicit Association Test (IAT). Results from both explicit and implicit measurements showed that humans attribute higher levels of agency and experience to humanoid robots with eyes (i.e. eyelike facial features) compared to robots without eyes. The results have great practical relevance to humanoid robot technology as the presence or absence of eyes in humanoid robots could have a fundamental effect on human-robot interaction.}, urldate = {2026-02-10}, journal = {Consciousness and Cognition}, author = {Hietanen, Jari K. and Linnunsalo, Samuli and Küster, Dennis}, month = jan, year = {2026}, keywords = {Eyes, Humanoid robot, Implicit association test, Mind attribution, Visual appearance}, pages = {103963}, file = {ScienceDirect Full Text PDF:C\:\\Users\\kuest\\Zotero\\storage\\PG3LR6UQ\\Hietanen et al. - 2026 - The impact of eyes on attributions of agency and experience in humanoid robots.pdf:application/pdf;ScienceDirect Snapshot:C\:\\Users\\kuest\\Zotero\\storage\\3SZ44XCT\\S1053810025001564.html:text/html}, } @inproceedings{pahuja_gtanet_2025, title = {{GTAnet}: {Geometry}-{Guided} {Temporal} {Attention} for {EEG}-{Based} {Sound} {Source} {Tracking} in {Cocktail} {Party} {Scenarios}}, shorttitle = {{GTAnet}}, url = {https://www.isca-archive.org/interspeech_2025/pahuja25_interspeech.html}, doi = {10.21437/Interspeech.2025-1887}, urldate = {2026-02-10}, author = {Pahuja, Saurav and Ivucic, Gabriel and Cai, Siqi and Da Silva, Dashanka and Li, Haizhou and Schultz, Tanja}, year = {2025}, pages = {5543--5547}, file = {Full Text PDF:C\:\\Users\\kuest\\Zotero\\storage\\JFRFK8LH\\Pahuja et al. - 2025 - GTAnet Geometry-Guided Temporal Attention for EEG-Based Sound Source Tracking in Cocktail Party Sce.pdf:application/pdf}, } @inproceedings{abrunhosarodrigues2026qualityassurance, title= {Controlled Large Scale Synthetic Motion Dataset Generation Leveraging Text-to-Motion and Sample-Wise Quality Assurance}, author = {Abrunhosa Rodrigues, Lourenço and Wenzel, Markus and Putze, Felix}, series = {BIOSIGNALS 2026}, year = {2026}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/AbrunhosaRodrigues_BIOSIGNALS2026_Controlled_Large_Sacle_Synthetic_Motion_Dataset_Generation_Leveraging_Text_to_Motion_and_Sample_Wise_Quality_Assurance.pdf}, abstract = {Learning representations of complex health data, such as human motion over the evolution of impairments, requires highly structured datasets with given temporal dependencies and reliable ground truth information. Collecting such data from humans is a costly endeavor, and subject to noise and confounders that make it difficult to attain these properties. Synthesizing data using text-to-motion models offers a solution to these problems, but requires an efficient and effective quality assurance process at the sample level that, until this work, did not exist. In this work we evaluate how MoBERT sample quality metrics align with human evaluations of sample naturalness and faithfulness. We design an efficient and highly scalable quality assurance protocol that can be used to verify the validity of samples in large scale synthetic human motion datasets. We generate a synthetic dataset containing thousands of samples, swiftly identify the samples with unsuitable quality, and show, with an activity recognition model, that these poor quality samples are indeed different from their higher quality counterparts, observing a 10\% point drop in performance when recognizing the activity represented by poor quality samples.} } @article{xia2025dt, title = {Towards Human Modeling for Human-Robot Collaboration and Digital Twins in Industrial Environments: Research Status, Prospects, and Challenges}, journal = {Robotics and Computer-Integrated Manufacturing}, volume = {95}, pages = {103043}, year = {2025}, issn = {0736-5845}, doi = {https://doi.org/10.1016/j.rcim.2025.103043}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/RCIM2025.pdf}, author = {Xia, Guoyi and Ghrairi, Zied and Wuest, Thorsten and Hribernik, Karl and Heuermann, Aaron and Liu, Furui and Liu, Hui and Thoben, Klaus-Dieter}, abstract = {Human-Robot Collaboration (HRC) and Digital Twins (DT) have significantly advanced industrial development and digital transformation. Human representations and models are essential in Industry 5.0, where human-centric is one of the key features. Despite the growing interest in human models for HRC and DT, a comprehensive overview of these models and enabling technologies currently needs to be provided. This paper aims to present the research status, prospects, applications, and challenges of human modeling for HRC and DT in industrial environments. This paper adopts a Systematic Literature Review (SLR) approach. Moreover, a framework is proposed to systematize human modeling aspects, the technologies used by robots for modeling, and the applications of human models throughout various lifecycle stages. The modeled aspects are categorized into physical and behavior models, with behavior models further divided into perception, cognition, and execution models. The technology is structured hierarchically into input, process, and output layers. Applications of the models are discussed across design, manufacturing, and service phases. The research status is examined in terms of human aspects and relevant technologies, identifying current limitations. Based on this, future prospects to address these limitations are discussed. Furthermore, the challenges in advancing current research towards these prospects are identified, focusing on model fidelity, individual-specific models, sensing, and computation. This research aims to support future human modeling in HRC and DT, contributing to safety, efficiency, and human well-being in industrial environments.} } @book{biostec2026, title = {Proceedings of the 19th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1-4}, shorttitle = {Proceedings of BIOSTEC 2026}, author = {Senthil, Swathi and Liu, Hui and Gamboa, Hugo and et al.}, editor = {Bahnemann, Janina and Fudickar, Sebastian and Mercaldo, Francesco and Solé-Casals, Jordi and Liu, Hui and Kaldoudi, Eleni and Gamboa, Hugo}, publisher = {{INSTICC}}, isbn = {978-989-758-802-0}, issn = {2184-4305}, year = {2026}, doi = {10.5220/0000217200004070}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/BIOSTEC_2026_Proceedings_Volume1.pdf} } @inproceedings{zheng2026sensorarrayBP, title = {Influence of Multi-Wavelength Sensor Array Design on Signal Stability and Application in Blood Pressure Detection}, author = {Zheng, Yuke and Yu, Long and Zhou, Ruishi and Hu, Yuchen and Wang, Hongwei and Liu, Hui and Ye, Xuesong and Zhou, Congcong}, booktitle = {Proceedings of the 19th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2026) - Volume 1: BIOSIGNALS}, pages = {371--375}, organization = {INSTICC}, publisher = {SCITEPRESS - Science and Technology Publications}, year = {2026}, isbn = {978-989-758-802-0}, issn = {2184-4305}, doi = {}, url = {https://www.csl.uni-bremen.de/cms/images/documents/publications/Zheng_BIOSIGNALS2026.pdf}, abstract = {Hypertension has emerged as a critical global public health challenge, underscoring the pressing need for continuous, non-invasive, and reliable blood pressure (BP) monitoring technologies. Wearable devices have garnered increasing attention as a promising solution to meet this demand. This paper analyses the influence of multi-wavelength sensor design in wearable systems on the accuracy and broader applicability of BP measurement techniques, drawing upon principles from photoplethysmography (PPG), optical spectroscopy and signal processing methodologies. The integration of multi-wavelength sensing represents a paradigm shift in wearable BP monitoring, offering enhanced noise suppression, improved physiological specificity, and greater adaptability across diverse populations. Despite ongoing challenges related to device miniaturization, power efficiency and algorithmic robustness, recent advances in sensor engineering and data-driven modeling approaches hold substantial potential for enabling the next generation of wearable BP monitors. These innovations may ultimately transform hypertension management in both clinical and home-based healthcare settings.} } @inproceedings{paul2026silhouette, title={Silhouette extraction from depth sensors for older adult monitoring at nursing homes}, author={Paul, Rinu Elizabeth and Devasia, Jomit Othalamattamthadthil and Kock, Pantea and Schultz, Tanja}, booktitle={Eighteenth International Conference on Machine Vision (ICMV 2025)}, volume={14114}, pages={759--766}, year={2026}, organization={SPIE}, doi={}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/Silhouette_extraction.pdf}, abstract = {Human monitoring is a key research area in healthcare, sports, and rehabilitation. Continuous, stress-free monitoring in natural environments requires non-wearable, non-invasive data acquisition methods. We addressed this need using depth sensors to extract human silhouettes without markers. However, markerless depth data collection presents challenges, such as noise and occlusions, which require robust feature extraction. We installed depth sensors in resident rooms at a nursing home and developed a silhouette-based envelope extraction pipeline using background subtraction and edge detection. To counterbalance the multi-person occlusion, we employed an envelope separation strategy for depth sensors. The extracted silhouettes were evaluated, achieving a maximum similarity of 98% to the ground truth. These silhouettes supported use cases such as fall detection and room occupancy monitoring, achieving a 94.85% F1 score in LSTM-based fall detection and a 96.82% F1 score in CNN+LSTM-based occupancy detection, demonstrating their real-world effectiveness. Despite challenges with occlusions and artifacts, this represents a reliable, non-invasive solution for continuous monitoring of older adults and shows potential for further applications, including gait analysis and activity recognition in healthcare and assisted living settings.}, } @inproceedings{paul2026depth, author={Paul, Rinu Elizabeth and Deichsel, Lucas and Schultz, Tanja}, title={Depth Sensor Based AI-Services for Nursing Homes}, booktitle={Artificial Intelligence for Healthcare, and Hybrid Models for Coupling Deductive and Inductive Reasoning}, year={2026}, publisher={Springer Nature Switzerland}, address={Cham}, pages={323--335}, isbn={978-3-032-16708-8}, doi={10.1007/978-3-032-16708-8_27}, url={https://www.csl.uni-bremen.de/cms/images/documents/publications/DepthSensor_Based_AI-Services_for_Nursing_Homes.pdf}, abstract={Falls are a frequent and critical event among older adults, often leading to severe consequences such as injuries, loss of independence, fear of walking, and even death. Therefore, it is essential to detect and prevent them. AI services in homes and nursing facilities enable early fall detection and timely support. Another major concern in nursing homes and clinics is the frequency of bed-exit attempts by residents or patients who cannot stand independently. These individuals often overlook their limitations and attempt to get out of bed alone, increasing the risk of falling. Our approach focuses on bed-exit detection to notify caregivers in real time, potentially preventing these incidents. We present a system that uses depth video to detect falls and bed-exit attempts among older adults. A configuration interface is developed to provide seamless access to fall and bed-exit detection functionalities and their results. The interface is compatible with various operating systems and optimized for both CPU and GPU versions, making it suitable for home and nursing facility applications. Our system achieves 68% accuracy and a 69% F1-score for fall detection, and 82% accuracy and an 88% F1-score for bed-exit detection. Room occupancy detection, which determines whether an older adult is present in the room, achieved 92% accuracy and an 89% F1-score. This work demonstrates significant potential to enhance services that improve assisted living environments.} }