Compensation of Recording Position Shifts for a Myoelectric Silent Speech Recognizerby Michael Wand, Christopher Schulte, Matthias Janke, Tanja Schultz
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.
Reference:
Compensation of Recording Position Shifts for a Myoelectric Silent Speech Recognizer (Michael Wand, Christopher Schulte, Matthias Janke, Tanja Schultz), In The 39th International Conference on Acoustics, Speech, and Signal Processing, 2014. (ICASSP 2014)
Bibtex Entry:
@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}
}