Inter-experimental discrepancy in facial muscle activity during vowel utterance

This paper analyses the inter-experimental similarities in the muscle activation during vowel sound production by an individual. Surface electromyography has been used as an indicator of muscle activity and independent component analysis has been used to separate the electrical activity from different muscles. The results indicate that there is a ‘reasonable’ relationship between muscle activities of the corresponding muscles when the experiments are repeated. The results demonstrate that when people speak, they use a similar set of muscles when they repeat the same sound. The results also indicate that there is a variation when the same sound is spoken at different speeds of utterances. This can be attributable to the lack of audio feedback when the same sound is uttered.

[1]  D. Stegeman,et al.  A surface EMG electrode for the simultaneous observation of multiple facial muscles , 2003, Journal of Neuroscience Methods.

[2]  S. Kumar,et al.  EMG based voice recognition , 2004, Proceedings of the 2004 Intelligent Sensors, Sensor Networks and Information Processing Conference, 2004..

[3]  H. Devries.  MUSCLES ALIVE-THEIR FUNCTIONS REVEALED BY ELECTROMYOGRAPHY , 1976 .

[4]  Aapo Hyvärinen,et al.  Fast and robust fixed-point algorithms for independent component analysis , 1999, IEEE Trans. Neural Networks.

[5]  J. Basmajian.  Muscles Alive—their functions revealed by electromyography , 1963 .

[6]  Marimuthu Palaniswami,et al.  Hand gestures for HCI using ICA of EMG , 2006 .

[7]  Carl D. Meyer,et al.  Matrix Analysis and Applied Linear Algebra , 2000 .

[8]  Xianggui Qu,et al.  Multivariate Data Analysis , 2007, Technometrics.

[9]  Thomas W. Parsons,et al.  Voice and Speech Processing , 1986 .

[10]  Francesco Carlo Morabito,et al.  A Morlet wavelet classification technique for ICA filtered sEMG experimental data , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[11]  Seungjin Choi,et al.  Independent Component Analysis , 2009, Handbook of Natural Computing.

[12]  Hideo Nakamura,et al.  The application of independent component analysis to the multi-channel surface electromyographic signals for separation of motor unit action potential trains: part I-measuring techniques. , 2004, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[13]  Toshiaki Sugimura,et al.  "Unvoiced speech recognition using EMG - mime speech recognition" , 2003, CHI Extended Abstracts.

[14]  A. J. Fridlund,et al.  Guidelines for human electromyographic research. , 1986, Psychophysiology.

[15]  Kevin Englehart,et al.  A multi-expert speech recognition system using acoustic and myoelectric signals , 2002, Proceedings of the Second Joint 24th Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society] [Engineering in Medicine and Biology.