Performance analysis of various single channel speech enhancement algorithms for automatic speech recognition

Myung Suk Song, Chang Heon Lee, Hong Goo Kang

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

2 Citations (Scopus)

Abstract

This paper analyzes the performance of various single channel speech enhancement systems when they are applied to automatic speech recognition (ASR) systems as a preprocessor. Until now the researches on speech enhancement algorithms have focused on improving the perceptual quality of speech signal. However, it has not been verified yet whether the improvements of the perceptual quality also increase the speech recognition rate. By investigating several enhancement modules designed for improving the perceptual quality, we analyze the relationship between a speech recognizer and speech enhancement systems. Simulation results show that the decision-directed method and speech absence probability (SAP) estimation proposed for improving perceptual quality influence adverse effects to the speech recognition performance.

Original languageEnglish
Title of host publicationINTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP
PublisherInternational Speech Communication Association
Pages1451-1454
Number of pages4
Volume3
ISBN (Print)9781604234497
Publication statusPublished - 2006 Jan 1
EventINTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP - Pittsburgh, PA, United States
Duration: 2006 Sep 172006 Sep 21

Other

OtherINTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP
CountryUnited States
CityPittsburgh, PA
Period06/9/1706/9/21

Fingerprint

Speech enhancement
Speech recognition

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

Song, M. S., Lee, C. H., & Kang, H. G. (2006). Performance analysis of various single channel speech enhancement algorithms for automatic speech recognition. In INTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP (Vol. 3, pp. 1451-1454). International Speech Communication Association.
Song, Myung Suk ; Lee, Chang Heon ; Kang, Hong Goo. / Performance analysis of various single channel speech enhancement algorithms for automatic speech recognition. INTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP. Vol. 3 International Speech Communication Association, 2006. pp. 1451-1454
@inproceedings{e18a7c49ab8b426dada709391e941cdf,
title = "Performance analysis of various single channel speech enhancement algorithms for automatic speech recognition",
abstract = "This paper analyzes the performance of various single channel speech enhancement systems when they are applied to automatic speech recognition (ASR) systems as a preprocessor. Until now the researches on speech enhancement algorithms have focused on improving the perceptual quality of speech signal. However, it has not been verified yet whether the improvements of the perceptual quality also increase the speech recognition rate. By investigating several enhancement modules designed for improving the perceptual quality, we analyze the relationship between a speech recognizer and speech enhancement systems. Simulation results show that the decision-directed method and speech absence probability (SAP) estimation proposed for improving perceptual quality influence adverse effects to the speech recognition performance.",
author = "Song, {Myung Suk} and Lee, {Chang Heon} and Kang, {Hong Goo}",
year = "2006",
month = "1",
day = "1",
language = "English",
isbn = "9781604234497",
volume = "3",
pages = "1451--1454",
booktitle = "INTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP",
publisher = "International Speech Communication Association",

}

Song, MS, Lee, CH & Kang, HG 2006, Performance analysis of various single channel speech enhancement algorithms for automatic speech recognition. in INTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP. vol. 3, International Speech Communication Association, pp. 1451-1454, INTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP, Pittsburgh, PA, United States, 06/9/17.

Performance analysis of various single channel speech enhancement algorithms for automatic speech recognition. / Song, Myung Suk; Lee, Chang Heon; Kang, Hong Goo.

INTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP. Vol. 3 International Speech Communication Association, 2006. p. 1451-1454.

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

TY - GEN

T1 - Performance analysis of various single channel speech enhancement algorithms for automatic speech recognition

AU - Song, Myung Suk

AU - Lee, Chang Heon

AU - Kang, Hong Goo

PY - 2006/1/1

Y1 - 2006/1/1

N2 - This paper analyzes the performance of various single channel speech enhancement systems when they are applied to automatic speech recognition (ASR) systems as a preprocessor. Until now the researches on speech enhancement algorithms have focused on improving the perceptual quality of speech signal. However, it has not been verified yet whether the improvements of the perceptual quality also increase the speech recognition rate. By investigating several enhancement modules designed for improving the perceptual quality, we analyze the relationship between a speech recognizer and speech enhancement systems. Simulation results show that the decision-directed method and speech absence probability (SAP) estimation proposed for improving perceptual quality influence adverse effects to the speech recognition performance.

AB - This paper analyzes the performance of various single channel speech enhancement systems when they are applied to automatic speech recognition (ASR) systems as a preprocessor. Until now the researches on speech enhancement algorithms have focused on improving the perceptual quality of speech signal. However, it has not been verified yet whether the improvements of the perceptual quality also increase the speech recognition rate. By investigating several enhancement modules designed for improving the perceptual quality, we analyze the relationship between a speech recognizer and speech enhancement systems. Simulation results show that the decision-directed method and speech absence probability (SAP) estimation proposed for improving perceptual quality influence adverse effects to the speech recognition performance.

UR - http://www.scopus.com/inward/record.url?scp=44949156594&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=44949156594&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:44949156594

SN - 9781604234497

VL - 3

SP - 1451

EP - 1454

BT - INTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP

PB - International Speech Communication Association

ER -

Song MS, Lee CH, Kang HG. Performance analysis of various single channel speech enhancement algorithms for automatic speech recognition. In INTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP. Vol. 3. International Speech Communication Association. 2006. p. 1451-1454