SPEECH RECOGNITION IN NOISY ENVIRONMENT USING WEIGHTED PROJECTION-BASED LIKELIHOOD MEASURE

Won Ho Shin; Weon Goo Kim; Chungyong Lee; Il Whan Cha

SPEECH RECOGNITION IN NOISY ENVIRONMENT USING WEIGHTED PROJECTION-BASED LIKELIHOOD MEASURE

Won Ho Shin, Weon Goo Kim, Chungyong Lee, Il Whan Cha

Department of Electrical and Electronic Engineering

Research output: Contribution to conference › Paper › peer-review

Abstract

This paper investigates a projection-based likelihood meaure that improves speech recognition performance in noisy environment. The projection-based likelihood measure is modified to give the weighting and projection effect and to reduce computational complexity. It is evaluated in sub-model based word recognition using semi-continuous hidden Markov model with speaker independent mode. Experimental results using proposed measure are reported for several performance factors: additive noise and noisy channel environment, various noise signals, and combination with other compensation method. In various noisy environments, performance improvements were achieved compared to the previously existing methods.

Original language	English
Publication status	Published - 1998
Event	5th International Conference on Spoken Language Processing, ICSLP 1998 - Sydney, Australia Duration: 1998 Nov 30 → 1998 Dec 4

Conference

Conference	5th International Conference on Spoken Language Processing, ICSLP 1998
Country/Territory	Australia
City	Sydney
Period	98/11/30 → 98/12/4

Bibliographical note

Funding Information:
This work was supported in part by Korea Telecommunication

Publisher Copyright:
© 1998. 5th International Conference on Spoken Language Processing, ICSLP 1998. All rights reserved.

All Science Journal Classification (ASJC) codes

Language and Linguistics
Linguistics and Language

Cite this

@conference{c681989ef5704988a23ef72290d23168,

title = "SPEECH RECOGNITION IN NOISY ENVIRONMENT USING WEIGHTED PROJECTION-BASED LIKELIHOOD MEASURE",

abstract = "This paper investigates a projection-based likelihood meaure that improves speech recognition performance in noisy environment. The projection-based likelihood measure is modified to give the weighting and projection effect and to reduce computational complexity. It is evaluated in sub-model based word recognition using semi-continuous hidden Markov model with speaker independent mode. Experimental results using proposed measure are reported for several performance factors: additive noise and noisy channel environment, various noise signals, and combination with other compensation method. In various noisy environments, performance improvements were achieved compared to the previously existing methods.",

author = "Shin, {Won Ho} and Kim, {Weon Goo} and Chungyong Lee and Cha, {Il Whan}",

note = "Funding Information: This work was supported in part by Korea Telecommunication Publisher Copyright: {\textcopyright} 1998. 5th International Conference on Spoken Language Processing, ICSLP 1998. All rights reserved.; 5th International Conference on Spoken Language Processing, ICSLP 1998 ; Conference date: 30-11-1998 Through 04-12-1998",

year = "1998",

language = "English",

}

TY - CONF

T1 - SPEECH RECOGNITION IN NOISY ENVIRONMENT USING WEIGHTED PROJECTION-BASED LIKELIHOOD MEASURE

AU - Shin, Won Ho

AU - Kim, Weon Goo

AU - Lee, Chungyong

AU - Cha, Il Whan

N1 - Funding Information: This work was supported in part by Korea Telecommunication Publisher Copyright: © 1998. 5th International Conference on Spoken Language Processing, ICSLP 1998. All rights reserved.

PY - 1998

Y1 - 1998

N2 - This paper investigates a projection-based likelihood meaure that improves speech recognition performance in noisy environment. The projection-based likelihood measure is modified to give the weighting and projection effect and to reduce computational complexity. It is evaluated in sub-model based word recognition using semi-continuous hidden Markov model with speaker independent mode. Experimental results using proposed measure are reported for several performance factors: additive noise and noisy channel environment, various noise signals, and combination with other compensation method. In various noisy environments, performance improvements were achieved compared to the previously existing methods.

AB - This paper investigates a projection-based likelihood meaure that improves speech recognition performance in noisy environment. The projection-based likelihood measure is modified to give the weighting and projection effect and to reduce computational complexity. It is evaluated in sub-model based word recognition using semi-continuous hidden Markov model with speaker independent mode. Experimental results using proposed measure are reported for several performance factors: additive noise and noisy channel environment, various noise signals, and combination with other compensation method. In various noisy environments, performance improvements were achieved compared to the previously existing methods.

UR - http://www.scopus.com/inward/record.url?scp=85128396607&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85128396607&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85128396607

T2 - 5th International Conference on Spoken Language Processing, ICSLP 1998

Y2 - 30 November 1998 through 4 December 1998

ER -

SPEECH RECOGNITION IN NOISY ENVIRONMENT USING WEIGHTED PROJECTION-BASED LIKELIHOOD MEASURE

Abstract

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this