ABSTRACT
This paper presented our studies of automatic speech recognition based on myoelectric signal in the application of Chinese pronounce recognition. Facial myoelectric signal records the articulatory apparatus and thus allows us to recognize spoken words even in silence. In this way, communication is not prone to ambient noise and can be used for patients with language difficulties. Activity sections were segment from original data by moving average method combined with a threshold comparison. According to MES characteristic, the coefficients of time domain and frequency domain, wavelet energy and Mel-frequency cepstral coefficients are selected from the original data for speech recognition. The principal component analysis (PCA) method was applied to reduce dimension and generate a 24-dimensional feature vector. We examined different classifiers with optimized parameters and found that the support vector machine classifier performs the best among all. Our final system achieved a 90.04% accuracy rate on a 10 Chinese digit words task. Therefore, this approach can bring muscle speech recognition within a powerful potential in the application of silent speech.
- Schultz, T., & Wand, M. 2010. Modeling coarticulation in EMG-based continuous speech recognition. Speech Communication, 52(4), 341--353.Google ScholarDigital Library
- Thum Wei Seong, M. Z. Ibrahim, and D. J. Mulvaney, WADA-W: A Modified WADA SNR Estimator for Audio-Visual Speech Recognition, International Journal of Machine Learning and Computing vol. 9, no. 4, pp. 446--451, 2019.Google Scholar
- Jou, S. C. S., Maierhein, L., Schultz, T., & Waibel, A.. 2006. Articulatory Feature Classification using Surface Electromyography. IEEE International Conference on Acoustics. IEEE.Google Scholar
- B. Denby, T. Schultz, K. Honda, T. Hueber, J. M. Gilbert, and J. S. Brumberg. 2010. Silent speech interfaces. Speech Commun. 52, 4 (April 2010), 270--287. DOI=http://dx.doi.org/10.1016/j.specom.2009.08.002Google ScholarDigital Library
- Shaun V. Ault, Rene J. Perez, Chloe A. Kimble, and Jin Wang, On Speech Recognition Algorithms, International Journal of Machine Learning and Computing vol. 8, no. 6, pp. 518--523, 2018.Google Scholar
- Morse, M. S., Day, S. H., Trull, B., & Morse, H.. 1989. Use of myoelectric signals to recognize speech. Engineering in Medicine and Biology Society, 1989. Images of the Twenty-First Century. Proceedings of the Annual International Conference of the IEEE Engineering in. IEEE.Google ScholarCross Ref
- Chan, A. D. C., Englehart, K., Hudgins, B., & Lovely, D. F. 2002. A multi-expert speech recognition system using acoustic and myoelectric signals. Engineering in Medicine and Biology, 2002. 24th Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society EMBS/BMES Conference, 2002. Proceedings of the Second Joint. IEEEGoogle ScholarCross Ref
- Hiroyuki Manabe, Akira Hiraiwa, and Toshiaki Sugimura. 2003. Unvoiced speech recognition using EMG - mime speech recognition. In CHI '03 Extended Abstracts on Human Factors in Computing Systems (CHI EA '03). ACM, New York, NY, USA, 794--795. DOI: https://doi.org/10.1145/765891.765996Google ScholarDigital Library
- Fraiwan, L., Lweesy, K., Al-Nemrawi, A., Addabass, S., & Saifan, R.. 2011. Voiceless Arabic vowel recognition using facial EMG. Medical & Biological Engineering & Computing, 49(7), 811--818.Google ScholarCross Ref
- Dai Limei, Yao Xiaodong, Wang Pei, et al., The Application of EMG in Speech Recognition, Computer Application (China), January 2005, pp. 5--7.Google Scholar
- Y. Li, Y. Tian, Z. Xu and Z. Yang, 2014, Multi-channel sEMG detection and pattern recognition, 2014 9th IEEE Conference on Industrial Electronics and Applications, Hangzhou, pp. 845--850. DOI: 10.1109/ICIEA.2014.6931280Google Scholar
- Hudgins, B., Parker, P., Scott, R.N., 1993. A new strategy for multifunction myoelectric control. IEEE Trans. Biomed. Eng. 40, 82--94. httpS://dx.doi.org/10.1109/10.204774Google ScholarCross Ref
- Goldstein, E.A., Heaton, J.T., Kobler, J.B., Stanley, G.B., Hillman, R.E., 2004. Design and implementation of a hands-free electrolarynx device controlled by neck strap muscle electromyographic activity. IEEE Trans. Biomed. Eng. 51, 325--332. http://dx.doi.org/10.1109/TBME.2003.820373Google ScholarCross Ref
- F. B. Stulen and C. J. De Luca, 1981, Frequency Parameters of the Myoelectric Signal as a Measure of Muscle Conduction Velocity, in IEEE Transactions on Biomedical Engineering, vol. BME-28, no. 7, pp. 515--523, July 1981.doi: 10.1109/TBME.1981.324738Google ScholarCross Ref
- De Armas, W., Mamun, K. A., & Chau, T. 2014. Vocal frequency estimation and voicing state prediction with surface EMG pattern recognition. Speech Communication, 63--64, 15--26.Google Scholar
- Longting Xu and Zhen Yang, 2013, Speaker identification based on sparse subspace model, 2013 19th Asia-Pacific Conference on Communications (APCC), Denpasar, pp. 37--41. DOI: 10.1109/APCC.2013.6765912Google ScholarCross Ref
- C. Jorgensen and K. Binsted, 2005, Web Browser Control Using EMG Based Sub Vocal Speech Recognition, Proceedings of the 38th Annual Hawaii International Conference on System Sciences, Big Island, HI, USA, 2005, pp. 294c-294c. DOI: 10.1109/HICSS.2005.683Google ScholarDigital Library
- Kumar, Chandar & Ur Rehman, Faizan & Kumar, Shubash & Mehmood, Atif & Shabir, Ghulam. 2018. Analysis of MFCC and BFCC in a speaker identification system. 10.1109/ICOMET.2018.8346330.Google Scholar
- Ferda Ernawan and Nur Azman Abu, Efficient Discrete Tchebichef on Spectrum Analysis of Speech Recognition, International Journal of Machine Learning and Computing vol. 1, no. 1, pp. 1--6, 2011.Google Scholar
- Mitra, V., Nam, H., Espy-Wilson, C., Saltzman, E., & Goldstein, L.. 2011. Robust speech recognition with articulatory features using dynamic bayesian networks. The Journal of the Acoustical Society of America, 130(4), 2408.Google ScholarCross Ref
Index Terms
- Unvoiced Speech Recognition Algorithm Based on Myoelectric Signal
Recommendations
"Unvoiced speech recognition using EMG - mime speech recognition"
CHI EA '03: CHI '03 Extended Abstracts on Human Factors in Computing SystemsWe propose unvoiced speech recognition, "Mime Speech Recognition". It recognizes speech by observing the muscles associated with speech. It is not based on voice signals but electromyography (EMG). It will realize unvoiced communication, which is a new ...
On the Recognition of Cochlear Implant-Like Spectrally Reduced Speech With MFCC and HMM-Based ASR
This correspondence investigates the recognition of cochlear implant-like spectrally reduced speech (SRS) using mel frequency cepstral coefficient (MFCC) and hidden Markov model (HMM)-based automatic speech recognition (ASR). The SRS was synthesized ...
Speech-Input Speech-Output Communication for Dysarthric Speakers Using HMM-Based Speech Recognition and Adaptive Synthesis System
Dysarthria is a motor speech disorder that causes inability to control and coordinate one or more articulators. This makes it difficult for a dysarthric speaker to utter certain speech sound units, thereby producing poorly articulated, slurred, and ...
Comments