Host: The Japan Society of Mechanical Engineers
Name : [in Japanese]
Date : June 08, 2016 - June 11, 2016
Our objective of this study is the development of a perfect voice recognition system using multi-SEMG that are measured from the human neck. In order to establish this objective a SEMG analyzing system is experimentally developed. In this paper, we will talk about the voice recognition results using this system. Actually, we conducted experiment which investigated whether this system can distinguish korea language vowel and consonant. In this experiment, we used 4 channel SEMG measured from subject’s neck. Positions of electrodes were determined using our developed Monte Carlo method. This method is able to select suitable positions of electrodes to detect pronounced voice. An experiment was carried out to see whether korea language pronunciations were distinguished each other using our developed method. In this paper we will talk about the results of this experiment.
