Speech/Non-Speech Detection for Electro-Larynx Speech Using EMG

Anna Katharina Fuchs, Clemens Amon, Martin Hagmüller

Abstract

Electro-larynx speech (EL) is a possibility to re-obtain speech when the larynx is surgically removed or damaged. As currently available devices normally are hand-held, a new generation of EL devices would benefit from a hands-free version. In this work we use electromyographic (EMG) signals to investigate speech/nonspeech detection for EL speech. The muscle activity, which is represented by the EMG signal, correlates with the intention to produce speech sounds and therefore, the short-term energy can serve as a feature to make a speech/non-speech decision. We developed a data acquisition hardware to record EMG signals using surface electrodes. We then recorded a small database with parallel recordings of EMG and EL speech and used different approaches to classify the EMG signal into speech/non-speech sections. We compared the following envelope calculation methods: root mean square, Hilbert envelope, and low-pass filtered envelope, and different classification methods: single threshold, double threshold and a Gaussian mixture model based classification. This study suggests that the results are speaker dependent, i.e. they strongly depend on the signal-to-noise ratio of the EMG signal. We show that using low-pass filtered envelope together with double threshold detection outperforms the rest.

References

  1. Atkinson, J. E. (1978). Correlation analysis of the physiological factors controlling fundamental voice frequency. The journal of the Acoustical Society of America, 63(1):211-222.
  2. Freeman, D., Cosier, G., Southcott, C., and Boyd, I. (1989). The voice activity detector for the pan-european digital cellular mobile telephone service. In International Conference on Acoustics, Speech, and Signal Processing, pages 369-372.
  3. Goldstein, E. A., Heaton, J. T., Kobler, J. B., Stanley, G. B., and Hillman, R. E. (2004). Design and implementation of a hands-free electrolarynx device controlled by neck strap muscle electromyographic activity. Biomedical Engineering, IEEE Transactions on, 51(2):325-332.
  4. Heaton, J., Robertson, M., and Griffin, C. (2011). Development of a wireless electromyographically controlled electrolarynx voice prosthesis. In Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC, pages 5352- 5355.
  5. Kubert, H., Stepp, C., Zeitels, S.M. anad Gooey, J., Walsh, M., Prakash, S., Hillman, R., and Heaton, J. (2009). Electromyographic control of a hands-free electrolarynx using neck strap muscles. Journal of communication disorders, 42(3):211-225.
  6. Ooe, K. (2012). Development of controllable artificial larynx by neck myoelectric signal. Procedia Engineering, 47(0):869 - 872. 26th European Conference on Solid-State Transducers.
  7. Ooe, K., Villagran, C., and Fukuda, T. (2010). Development of the compact control system using of neck emg signal for welfare applications. In International Symposium on Micro-NanoMechatronics and Human Science (MHS), pages 127-132.
  8. Pineda-Rico, Z., Dieck-Assad, G., Martinez-Chapa, S., and Avila-Ortega, A. (2008). A switching capacitor cmos based device for hands-free electrolarynx activation using electromyographic signals. In Electronics, Robotics and Automotive Mechanics Conference, pages 8-13.
  9. Reynolds, D. A., Quatieri, T. F., and Dunn, R. B. (2000). Speaker verification using adapted gaussian mixture models. Digital signal processing, 10(1):19-41.
Download


Paper Citation


in Harvard Style

Katharina Fuchs A., Amon C. and Hagmüller M. (2015). Speech/Non-Speech Detection for Electro-Larynx Speech Using EMG . In Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2015) ISBN 978-989-758-069-7, pages 138-144. DOI: 10.5220/0005181401380144


in Bibtex Style

@conference{biosignals15,
author={Anna Katharina Fuchs and Clemens Amon and Martin Hagmüller},
title={Speech/Non-Speech Detection for Electro-Larynx Speech Using EMG},
booktitle={Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2015)},
year={2015},
pages={138-144},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005181401380144},
isbn={978-989-758-069-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2015)
TI - Speech/Non-Speech Detection for Electro-Larynx Speech Using EMG
SN - 978-989-758-069-7
AU - Katharina Fuchs A.
AU - Amon C.
AU - Hagmüller M.
PY - 2015
SP - 138
EP - 144
DO - 10.5220/0005181401380144