Unvoiced speech recognition using EMG - Mime Speech Recognition

Hiroyuki Manabe, Akira Hiraiwa, Toshiaki Sugimura

Research output: Chapter in Book/Report/Conference proceedingConference contribution

65 Citations (Scopus)


We propose unvoiced speech recognition, "Mime Speech Recognition". It recognizes speech by observing the muscles associated with speech. It is not based on voice signals but electromyography (EMG). It will realize unvoiced communication, which is a new communication style. Because voice signals are not used, it can be applied in noisy environments; it also supports people without vocal-cords and aphasics. In preliminary experiments, we try to recognize the 5 Japanese vowels. EMG signals from the 3 muscles that contribute greatly to the utterance of Japanese vowels are input to a neural network. The recognition accuracy is over 90% for the three subjects tested.

Original languageEnglish
Title of host publicationCHI'03 Extended Abstracts on Human Factors in Computing Systems, CHI EA'03
Number of pages2
Publication statusPublished - 2003
Externally publishedYes
EventConference on Human Factors in Computing Systems, CHI EA 2003 - Ft. Lauderdale, FL, United States
Duration: 2003 Apr 52003 Apr 10

Publication series

NameConference on Human Factors in Computing Systems - Proceedings


ConferenceConference on Human Factors in Computing Systems, CHI EA 2003
Country/TerritoryUnited States
CityFt. Lauderdale, FL


  • EMG
  • Neural network
  • Speech recognition
  • Vowel

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'Unvoiced speech recognition using EMG - Mime Speech Recognition'. Together they form a unique fingerprint.

Cite this