Research has been conducted into the recognition of speech utilizing the myoelectric signals exhibited by the muscles that shape the vocal tract.Myoelectric signals from four muscles sites were digitized along with the acoustic waveform. Energy, average magnitude, and standard deviation of the biopotentials served as inputs to a maximum likelihood classifier. Recognition is close to three times apriori for a ten word set with a 7 0 4 0 % chance of recognition within the first five choices of the maximum likelihood algorithm.
ACKNOWLEDGEMENTResearch has been done on a control scheme that attempts to recognize speech from the myoelectric signals (MES) exhibited by the muscles that help shape the vocal tract. In this study, the myoelectric signals from four muscle sites were digitized along with the acoustic waveform. A maximum likelihood pattern classifier was applied to three parameters of each MES: energy, average magnitude, and standard deviation. The results thus far yield several indications, including a time-variance of the MES. The goal of the current research is to obtain the best possible recognition in an attempt to approach a clinically acceptable level of accuracy (approaching 95%).
REVIEW