Abstract
This paper presents our studies of automatic speech recognition based on electromyographic biosignals captured from the articulatory muscles in the face using surface electrodes. We develop a phone-based speech recognizer and describe how the performance of this recognizer improves by carefully designing and tailoring the extraction of relevant speech feature toward electromyographic signals. Our experimental design includes the collection of audibly spoken speech simultaneously recorded as acoustic data using a close-speaking microphone and as electromyographic signals using electrodes. Our experiments indicate that electromyographic signals precede the acoustic signal by about 0.05-0.06 seconds. Furthermore, we introduce articulatory feature classifiers, which had recently shown to improved classical speech recognition significantly. We describe that the classification accuracy of articulatory features clearly benefits from the tailored feature extraction. Finally, these classifiers are integrated into the overall decoding framework applying a stream architecture. Our final system achieves a word error rate of 29.9% on a 100-word recognition task.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Fromkin, V., Ladefoged, P.: Electromyography in speech research. Phonetica 15 (1966)
Chan, A., Englehart, K., Hudgins, B., Lovely, D.: Hidden Markov model classification of myoelectric signals in speech. IEEE Engineering in Medicine and Biology Magazine 21(4), 143–146 (2002)
Jorgensen, C., Lee, D., Agabon, S.: Sub auditory speech recognition based on EMG signals. In: Proc. IJCNN, Portland, Oregon (July 2003)
Jorgensen, C., Binsted, K.: Web browser control using EMG based sub vocal speech recognition. In: Proc. HICSS, Hawaii (January 2005)
Betts, B., Jorgensen, C.: Small vocabulary communication and control using surface electromyography in an acoustically noisy environment. In: Proc. HICSS, Hawaii (January 2006)
Manabe, H., Hiraiwa, A., Sugimura, T.: Unvoiced speech recognition using EMG-Mime speech recognition. In: Proc. CHI, Ft. Lauderdale, Florida (April 2003)
Manabe, H., Zhang, Z.: Multi-stream HMM for EMG-based speech recognition. In: Proc. IEEE EMBS, San Francisco, California (September 2004)
Maier-Hein, L., Metze, F., Schultz, T., Waibel, A.: Session independent non-audible speech recognition using surface electromyography. In: Proc. ASRU, San Juan, Puerto Rico (November 2005)
Becker, K.: Varioport (2005), http://www.becker-meditec.de
Walliczek, M., Kraft, F., Jou, S.C., Schultz, T., Waibel, A.: Sub-word unit based non-audible speech recognition using surface electromyography. In: Proc. Interspeech, Pittsburgh, PA (September 2006)
Yu, H., Waibel, A.: Streaming the front-end of a speech recognizer. In: Proc. ICSLP, Beijing, China (2000)
Metze, F., Waibel, A.: A flexible stream architecture for ASR using articulatory features. In: Proc. ICSLP, Denver, CO (September 2002)
Jou, S.C., Schultz, T., Walliczek, M., Kraft, F., Waibel, A.: Towards continuous speech recognition using surface electromyography. In: Proc. Interspeech, Pittsburgh, PA (September 2006)
Jou, S.C., Schultz, T., Waibel, A.: Continuous electromyographic speech recognition with a multi-stream decoding architecture. In: Proc. ICASSP, Honolulu, Hawai’i (April 2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jou, SC.S., Schultz, T. (2008). Automatic Speech Recognition Based on Electromyographic Biosignals. In: Fred, A., Filipe, J., Gamboa, H. (eds) Biomedical Engineering Systems and Technologies. BIOSTEC 2008. Communications in Computer and Information Science, vol 25. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-92219-3_23
Download citation
DOI: https://doi.org/10.1007/978-3-540-92219-3_23
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-92218-6
Online ISBN: 978-3-540-92219-3
eBook Packages: Computer ScienceComputer Science (R0)