Robust and preceding speech detection using EMG

Hiroyuki 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
Pages5812-5815
Number of pages4
Publication statusPublished - 2005 Dec 1
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

Fingerprint

Acoustic noise
Experiments

Keywords

  • EMG
  • Speech
  • VAD (voice activity detection)

ASJC Scopus subject areas

  • Bioengineering

Cite this

Manabe, H., & Fukumoto, M. (2005). Robust and preceding speech detection using EMG. In Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005 (pp. 5812-5815). [1615810] (Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings; Vol. 7 VOLS).

Robust and preceding speech detection using EMG. / Manabe, Hiroyuki; Fukumoto, M.

Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005. 2005. p. 5812-5815 1615810 (Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings; Vol. 7 VOLS).

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

Manabe, H & Fukumoto, M 2005, Robust and preceding speech detection using EMG. in Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005., 1615810, Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, vol. 7 VOLS, pp. 5812-5815, 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005, Shanghai, China, 05/9/1.
Manabe H, Fukumoto M. Robust and preceding speech detection using EMG. In Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005. 2005. p. 5812-5815. 1615810. (Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings).
Manabe, Hiroyuki ; Fukumoto, M. / Robust and preceding speech detection using EMG. Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005. 2005. pp. 5812-5815 (Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings).
@inproceedings{99723f0f4a0447b28113bfcde8ce33f6,
title = "Robust and preceding speech detection using EMG",
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.",
keywords = "EMG, Speech, VAD (voice activity detection)",
author = "Hiroyuki Manabe and M. Fukumoto",
year = "2005",
month = "12",
day = "1",
language = "English",
isbn = "0780387406",
series = "Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings",
pages = "5812--5815",
booktitle = "Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005",

}

TY - GEN

T1 - Robust and preceding speech detection using EMG

AU - Manabe, Hiroyuki

AU - Fukumoto, M.

PY - 2005/12/1

Y1 - 2005/12/1

N2 - 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.

AB - 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.

KW - EMG

KW - Speech

KW - VAD (voice activity detection)

UR - http://www.scopus.com/inward/record.url?scp=33846895266&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846895266&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:33846895266

SN - 0780387406

SN - 9780780387409

T3 - Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings

SP - 5812

EP - 5815

BT - Proceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005

ER -