Title :
Use of myoelectric signals to recognize speech
Author :
Morse, Michael S. ; Day, Susan H. ; Trull, Barbara ; Morse, Herman
Author_Institution :
Dept. of Electr. Eng., Auburn Univ., AL, USA
Abstract :
It has been determined that the myoelectric signals (MES) from muscles associated with speech that are obtained using surface electrodes can be used to recognize speech at approximately five times a priori. The results of ten experiments have been evaluated using a maximum-likelihood recognition scheme and have consistently yielded similar recognition accuracy among several subjects. Individual word recognition from a ten-word set has approached 60%. Parameters studied have included energy, magnitude, and trial deviation. The results suggest that accuracies at a level suitable for use in a vocal prosthesis will require the development of a hybrid recognition algorithm utilizing either statistical and heuristic word separation or neural nets
Keywords :
bioelectric potentials; muscle; speech recognition; 10-word set; heuristic word separation; maximum-likelihood recognition scheme; myoelectric signals; neural nets; speech recognition; statistical word separation; surface electrodes; trial deviation; vocal prosthesis; Electrodes; Frequency domain analysis; Muscles; Neural networks; Neural prosthesis; Pattern recognition; Prosthetics; Resistors; Scattering; Speech recognition;
Conference_Titel :
Engineering in Medicine and Biology Society, 1989. Images of the Twenty-First Century., Proceedings of the Annual International Conference of the IEEE Engineering in
Conference_Location :
Seattle, WA
DOI :
10.1109/IEMBS.1989.96459
