Robust and preceding speech detection using EMG

H. Manabe, M. Fukumoto

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

2 Citations (Scopus)

Abstract

EMG-based VAD is proposed. It is generally known that EMG signals are not affected by acoustic noise and preceding voice. Robust but preceding detection of speech can be expected by using these features. The proposed method extracts one VAD parameter to judge speech or silence from among n EMG signal channels. Experiments are performed to confirm the effectiveness of the proposed method. The results show that some EMG signals reliably precede voice by 30ms or more. Compared with conventional audio VAD, the proposed method seldom drops the speech head and the method's performance is relatively insensitive to background noise.

Original languageEnglish
Title of host publicationProceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5812-5815
Number of pages4
ISBN (Print)0780387406, 9780780387409
DOIs
Publication statusPublished - 2005
Externally publishedYes
Event2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005 - Shanghai, China
Duration: 2005 Sep 12005 Sep 4

Publication series

NameAnnual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
Volume7 VOLS
ISSN (Print)0589-1019

Conference

Conference2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005
CountryChina
CityShanghai
Period05/9/105/9/4

Keywords

  • EMG
  • Speech
  • VAD (voice activity detection)

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Fingerprint Dive into the research topics of 'Robust and preceding speech detection using EMG'. Together they form a unique fingerprint.

Cite this