A Spectral Mapping Method for EMG-based Recognition of Silent Speech

Matthias Janke, Michael Wand, Tanja Schultz

2010

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.

References

  1. Sugie, N., Tsunoda, K.: A Speech Prosthesis Employing a Speech Synthesizer - Vowel Discrimination from Perioral Muscle Activities and Vowel Production. IEEE Trans. Biomed. Eng. 32 (1985) 485 - 490
  2. Chan, A., Englehart, K., Hudgins, B., Lovely, D.: Myoelectric Signals to Augment Speech Recognition. Medical and Biological Engineering and Computing 39 (2001) 500 - 506
  3. Jorgensen, C., Lee, D., Agabon, S.: Sub Auditory Speech Recognition Based on EMG/EPG Signals. In: Proceedings of International Joint Conference on Neural Networks (IJCNN), Portland, Oregon (2003) 3128 - 3133
  4. Jou, S.C., Schultz, T., Walliczek, M., Kraft, F., Waibel, A.: Towards Continuous Speech Recognition using Surface Electromyography. In: Proc. Interspeech, Pittsburgh, PA (2006) 573 - 576
  5. Schultz, T., Wand, M.: Modeling Coarticulation in Large Vocabulary EMG-based Speech Recognition. (Speech Communication Journal, 2009, to appear)
  6. Maier-Hein, L., Metze, F., Schultz, T., Waibel, A.: Session Independent Non-Audible Speech Recognition Using Surface Electromyography. In: IEEE Workshop on Automatic Speech Recognition and Understanding, San Juan, Puerto Rico (2005) 331 - 336
  7. Wand, M., Jou, S.C.S., Toth, A.R., Schultz, T.: Impact of Different Speaking Modes on EMGbased Speech Recognition. In: Proc. Interspeech. (2009)
  8. Welch, P.: The use of fast fourier transform for the estimation of power spectra: A method based on time averaging over short, modified periodograms. Audio and Electroacoustics, IEEE Transactions on 15 (1967) 70-73
Download


Paper Citation


in Harvard Style

Janke M., Wand M. and Schultz T. (2010). A Spectral Mapping Method for EMG-based Recognition of Silent Speech . In Proceedings of the 1st International Workshop on Bio-inspired Human-Machine Interfaces and Healthcare Applications - Volume 1: B-Interface, (BIOSTEC 2010) ISBN 978-989-674-020-7, pages 22-31. DOI: 10.5220/0002814100220031


in Bibtex Style

@conference{b-interface10,
author={Matthias Janke and Michael Wand and Tanja Schultz},
title={A Spectral Mapping Method for EMG-based Recognition of Silent Speech},
booktitle={Proceedings of the 1st International Workshop on Bio-inspired Human-Machine Interfaces and Healthcare Applications - Volume 1: B-Interface, (BIOSTEC 2010)},
year={2010},
pages={22-31},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002814100220031},
isbn={978-989-674-020-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 1st International Workshop on Bio-inspired Human-Machine Interfaces and Healthcare Applications - Volume 1: B-Interface, (BIOSTEC 2010)
TI - A Spectral Mapping Method for EMG-based Recognition of Silent Speech
SN - 978-989-674-020-7
AU - Janke M.
AU - Wand M.
AU - Schultz T.
PY - 2010
SP - 22
EP - 31
DO - 10.5220/0002814100220031