筋電ボコーダ

抄録

Verbal communication acts one of the most important role in our daily life, so it is very valuable to develop an artificial laryngeal device for laryngectomized patients. In this paper, we propose a new method, which can discriminate phonetic sounds based on EMG, using a neural network and hidden Markov models. Experimental results show that the phonetic sound can be discriminated from EMG.