Multi-stream HMM for EMG-based speech recognition

Hiroyuki Manabe, Z. Zhang

Research output: Contribution to journalConference article

34 Citations (Scopus)

Abstract

A technique for improving the recognition accuracy of EMG-based speech recognition by applying existing speech recognition technologies is proposed. The authors have proposed an EMG-based speech recognition system that requires only mouth movements, voice need not be generated. A multi-stream HMM (Hidden Markov Model) and feature extraction technique are applied to EMG-based speech recognition. 3 channel facial EMG signals are collected from ten subjects when uttering 10 Japanese isolated digits. One channel corresponds to one stream. By examining various features, we found that the delta component of the static parameter leads to higher accuracy. Compared to equal stream weighting, the individual optimization of stream weights increased recognition accuracy by 4. 0% which corresponds to a 12.8% reduction in error rate. This result shows that multi-stream HMM is effective for the classification of EMG.

Original languageEnglish
Pages (from-to)4389-4392
Number of pages4
JournalAnnual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
Volume26 VI
Publication statusPublished - 2004 Dec 1
Externally publishedYes
EventConference Proceedings - 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2004 - San Francisco, CA, United States
Duration: 2004 Sep 12004 Sep 5

Fingerprint

Hidden Markov models
Speech recognition
Feature extraction

Keywords

  • EMG
  • Multi-stream HMM
  • Speech recognition

ASJC Scopus subject areas

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

Cite this

Multi-stream HMM for EMG-based speech recognition. / Manabe, Hiroyuki; Zhang, Z.

In: Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, Vol. 26 VI, 01.12.2004, p. 4389-4392.

Research output: Contribution to journalConference article

@article{9ce2e1bc55ff47caa5e5099510afac88,
title = "Multi-stream HMM for EMG-based speech recognition",
abstract = "A technique for improving the recognition accuracy of EMG-based speech recognition by applying existing speech recognition technologies is proposed. The authors have proposed an EMG-based speech recognition system that requires only mouth movements, voice need not be generated. A multi-stream HMM (Hidden Markov Model) and feature extraction technique are applied to EMG-based speech recognition. 3 channel facial EMG signals are collected from ten subjects when uttering 10 Japanese isolated digits. One channel corresponds to one stream. By examining various features, we found that the delta component of the static parameter leads to higher accuracy. Compared to equal stream weighting, the individual optimization of stream weights increased recognition accuracy by 4. 0{\%} which corresponds to a 12.8{\%} reduction in error rate. This result shows that multi-stream HMM is effective for the classification of EMG.",
keywords = "EMG, Multi-stream HMM, Speech recognition",
author = "Hiroyuki Manabe and Z. Zhang",
year = "2004",
month = "12",
day = "1",
language = "English",
volume = "26 VI",
pages = "4389--4392",
journal = "Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference",
issn = "1557-170X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Multi-stream HMM for EMG-based speech recognition

AU - Manabe, Hiroyuki

AU - Zhang, Z.

PY - 2004/12/1

Y1 - 2004/12/1

N2 - A technique for improving the recognition accuracy of EMG-based speech recognition by applying existing speech recognition technologies is proposed. The authors have proposed an EMG-based speech recognition system that requires only mouth movements, voice need not be generated. A multi-stream HMM (Hidden Markov Model) and feature extraction technique are applied to EMG-based speech recognition. 3 channel facial EMG signals are collected from ten subjects when uttering 10 Japanese isolated digits. One channel corresponds to one stream. By examining various features, we found that the delta component of the static parameter leads to higher accuracy. Compared to equal stream weighting, the individual optimization of stream weights increased recognition accuracy by 4. 0% which corresponds to a 12.8% reduction in error rate. This result shows that multi-stream HMM is effective for the classification of EMG.

AB - A technique for improving the recognition accuracy of EMG-based speech recognition by applying existing speech recognition technologies is proposed. The authors have proposed an EMG-based speech recognition system that requires only mouth movements, voice need not be generated. A multi-stream HMM (Hidden Markov Model) and feature extraction technique are applied to EMG-based speech recognition. 3 channel facial EMG signals are collected from ten subjects when uttering 10 Japanese isolated digits. One channel corresponds to one stream. By examining various features, we found that the delta component of the static parameter leads to higher accuracy. Compared to equal stream weighting, the individual optimization of stream weights increased recognition accuracy by 4. 0% which corresponds to a 12.8% reduction in error rate. This result shows that multi-stream HMM is effective for the classification of EMG.

KW - EMG

KW - Multi-stream HMM

KW - Speech recognition

UR - http://www.scopus.com/inward/record.url?scp=11044234619&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=11044234619&partnerID=8YFLogxK

M3 - Conference article

VL - 26 VI

SP - 4389

EP - 4392

JO - Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference

JF - Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference

SN - 1557-170X

ER -