HMM Parameter Adaptation Using the Truncated First-Order VTS and EM Algorithm for Robust Speech Recognition

This paper presents a framework of HMM parameter adaptation technique for improving automatic speech recognition (ASR) performance in the noisy environments, which online combines the clean hidden Markov models (HMMs) with the noise model. Based on the given composite HMM corresponding to the initia...

Full description

Saved in:
Bibliographic Details
Published inComputational Intelligence and Security pp. 979 - 984
Main Authors Shen, Haifeng, Li, Qunxia, Guo, Jun, Liu, Gang
Format Book Chapter
LanguageEnglish
Published Berlin, Heidelberg Springer Berlin Heidelberg 2005
SeriesLecture Notes in Computer Science
Subjects
Automatic Speech Recognition
Noise Model
Noisy Environment
Recognition Rate
Speech Recognition
Online AccessGet full text
ISBN9783540308188
3540308180
ISSN0302-9743
1611-3349
DOI10.1007/11596448_145

Cover

Abstract This paper presents a framework of HMM parameter adaptation technique for improving automatic speech recognition (ASR) performance in the noisy environments, which online combines the clean hidden Markov models (HMMs) with the noise model. Based on the given composite HMM corresponding to the initial recognition pass result and truncated vector Taylor series, the noise model in the cepstral domain is updated and refined using iterative Expectation-Maximization (EM) algorithm under maximum likelihood (ML) criterion. Experiments results show that the presented approach in this paper is found to greatly improve recognition performance under mismatched conditions.
AbstractList This paper presents a framework of HMM parameter adaptation technique for improving automatic speech recognition (ASR) performance in the noisy environments, which online combines the clean hidden Markov models (HMMs) with the noise model. Based on the given composite HMM corresponding to the initial recognition pass result and truncated vector Taylor series, the noise model in the cepstral domain is updated and refined using iterative Expectation-Maximization (EM) algorithm under maximum likelihood (ML) criterion. Experiments results show that the presented approach in this paper is found to greatly improve recognition performance under mismatched conditions.
Author Shen, Haifeng
Li, Qunxia
Liu, Gang
Guo, Jun
Author_xml – sequence: 1
  givenname: Haifeng
  surname: Shen
  fullname: Shen, Haifeng
  email: shen_hai_feng@126.com
  organization: Beijing University of Posts and Telecommunications, Beijing, China
– sequence: 2
  givenname: Qunxia
  surname: Li
  fullname: Li, Qunxia
  email: kellylqx@163.com
  organization: University of Science and Technology Beijing, Beijing, China
– sequence: 3
  givenname: Jun
  surname: Guo
  fullname: Guo, Jun
  email: guojun@bupt.edu.cn
  organization: Beijing University of Posts and Telecommunications, Beijing, China
– sequence: 4
  givenname: Gang
  surname: Liu
  fullname: Liu, Gang
  email: lg@pris.edu.cn
  organization: Beijing University of Posts and Telecommunications, Beijing, China
BookMark eNpNUMtuwjAQdFsqFSi3foDPldLuxnEcHxGCUglExaPXyHEcSIEY2eb_m7Q9dC-7mtkZaWZAeo1tDCFPCC8IIF4RuUyTJMsx4TdkwHgCrIUkuyV9TBEjxhJ5R0ZSZD8cZJhlPdJvrziSImEPZOD9FwDEQsZ9cpwvl_RDOXU2wTg6LtUlqFDbhu583expOBi6dddGq2BKOqudD9HKle3r53ZDVVPS6ZKOT3vr6nA408o6urbF1Qe6uRijD3RttN03dWf5SO4rdfJm9LeHZDebbifzaLF6e5-MF5FH4DxC0InWsUCuhICCV8iBSRDdFKwsNI9RKRVXoNJSc6ggVbrCViJBSZmyIXn-9fUX12YwLi-sPfocIe86zP93yL4B_cpgRw
ContentType Book Chapter
Copyright Springer-Verlag Berlin Heidelberg 2005
Copyright_xml – notice: Springer-Verlag Berlin Heidelberg 2005
DOI 10.1007/11596448_145
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Mathematics
Computer Science
EISBN 3540315993
9783540315995
EISSN 1611-3349
Editor Yin, Hujun
Ma, Jianfeng
Jiao, Licheng
Liu, Jiming
Wang, Yuping
Hao, Yue
Cheung, Yiu-ming
Jiao, Yong-Chang
Editor_xml – sequence: 1
  givenname: Yue
  surname: Hao
  fullname: Hao, Yue
  email: yhao@xidian.edu.cn
– sequence: 2
  givenname: Jiming
  surname: Liu
  fullname: Liu, Jiming
  email: jiming@comp.hkbu.edu.hk
– sequence: 3
  givenname: Yuping
  surname: Wang
  fullname: Wang, Yuping
  email: ywang@xidian.edu.cn
– sequence: 4
  givenname: Yiu-ming
  surname: Cheung
  fullname: Cheung, Yiu-ming
  email: ymc@comp.hkbu.edu.hk
– sequence: 5
  givenname: Hujun
  surname: Yin
  fullname: Yin, Hujun
  email: h.yin@manchester.ac.uk
– sequence: 6
  givenname: Licheng
  surname: Jiao
  fullname: Jiao, Licheng
  email: lchjiao@mail.xidian.edu.cn
– sequence: 7
  givenname: Jianfeng
  surname: Ma
  fullname: Ma, Jianfeng
  email: ejfma@hotmail.com.cn
– sequence: 8
  givenname: Yong-Chang
  surname: Jiao
  fullname: Jiao, Yong-Chang
  email: ychjiao@xidian.edu.cn
EndPage 984
GroupedDBID -DT
-GH
-~X
1SB
29L
2HA
2HV
5QI
875
AASHB
ABMNI
ACGFS
ADCXD
AEFIE
ALMA_UNASSIGNED_HOLDINGS
EJD
F5P
FEDTE
HVGLF
LAS
LDH
P2P
RIG
RNI
RSU
SVGTG
VI1
~02
ID FETCH-LOGICAL-s1055-10c4cc2715a770b5f15039077777b3dbc521aaa2f0a6dc50f06acf1cc290a9963
ISBN 9783540308188
3540308180
ISSN 0302-9743
IngestDate Tue Jul 29 19:55:39 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-s1055-10c4cc2715a770b5f15039077777b3dbc521aaa2f0a6dc50f06acf1cc290a9963
PageCount 6
ParticipantIDs springer_books_10_1007_11596448_145
PublicationCentury 2000
PublicationDate 2005
PublicationDateYYYYMMDD 2005-01-01
PublicationDate_xml – year: 2005
  text: 2005
PublicationDecade 2000
PublicationPlace Berlin, Heidelberg
PublicationPlace_xml – name: Berlin, Heidelberg
PublicationSeriesSubtitle Lecture Notes in Artificial Intelligence
PublicationSeriesTitle Lecture Notes in Computer Science
PublicationSubtitle International Conference, CIS 2005, Xi’an, China, December 15-19, 2005, Proceedings Part I
PublicationTitle Computational Intelligence and Security
PublicationYear 2005
Publisher Springer Berlin Heidelberg
Publisher_xml – name: Springer Berlin Heidelberg
RelatedPersons Kleinberg, Jon M.
Mattern, Friedemann
Nierstrasz, Oscar
Tygar, Dough
Steffen, Bernhard
Kittler, Josef
Vardi, Moshe Y.
Weikum, Gerhard
Sudan, Madhu
Naor, Moni
Mitchell, John C.
Terzopoulos, Demetri
Pandu Rangan, C.
Kanade, Takeo
Hutchison, David
RelatedPersons_xml – sequence: 1
  givenname: David
  surname: Hutchison
  fullname: Hutchison, David
  organization: Lancaster University, UK
– sequence: 2
  givenname: Takeo
  surname: Kanade
  fullname: Kanade, Takeo
  organization: Carnegie Mellon University, Pittsburgh, USA
– sequence: 3
  givenname: Josef
  surname: Kittler
  fullname: Kittler, Josef
  organization: University of Surrey, Guildford, UK
– sequence: 4
  givenname: Jon M.
  surname: Kleinberg
  fullname: Kleinberg, Jon M.
  organization: Cornell University, Ithaca, USA
– sequence: 5
  givenname: Friedemann
  surname: Mattern
  fullname: Mattern, Friedemann
  organization: ETH Zurich, Switzerland
– sequence: 6
  givenname: John C.
  surname: Mitchell
  fullname: Mitchell, John C.
  organization: Stanford University, CA, USA
– sequence: 7
  givenname: Moni
  surname: Naor
  fullname: Naor, Moni
  organization: Weizmann Institute of Science, Rehovot, Israel
– sequence: 8
  givenname: Oscar
  surname: Nierstrasz
  fullname: Nierstrasz, Oscar
  organization: University of Bern, Switzerland
– sequence: 9
  givenname: C.
  surname: Pandu Rangan
  fullname: Pandu Rangan, C.
  organization: Indian Institute of Technology, Madras, India
– sequence: 10
  givenname: Bernhard
  surname: Steffen
  fullname: Steffen, Bernhard
  organization: University of Dortmund, Germany
– sequence: 11
  givenname: Madhu
  surname: Sudan
  fullname: Sudan, Madhu
  organization: Massachusetts Institute of Technology, MA, USA
– sequence: 12
  givenname: Demetri
  surname: Terzopoulos
  fullname: Terzopoulos, Demetri
  organization: University of California, Los Angeles, USA
– sequence: 13
  givenname: Dough
  surname: Tygar
  fullname: Tygar, Dough
  organization: University of California, Berkeley, USA
– sequence: 14
  givenname: Moshe Y.
  surname: Vardi
  fullname: Vardi, Moshe Y.
  organization: Rice University, Houston, USA
– sequence: 15
  givenname: Gerhard
  surname: Weikum
  fullname: Weikum, Gerhard
  organization: Max-Planck Institute of Computer Science, Saarbruecken, Germany
SSID ssj0002792
ssj0000316783
Score 1.2955346
Snippet This paper presents a framework of HMM parameter adaptation technique for improving automatic speech recognition (ASR) performance in the noisy environments,...
SourceID springer
SourceType Publisher
StartPage 979
SubjectTerms Automatic Speech Recognition
Noise Model
Noisy Environment
Recognition Rate
Speech Recognition
Title HMM Parameter Adaptation Using the Truncated First-Order VTS and EM Algorithm for Robust Speech Recognition
URI http://link.springer.com/10.1007/11596448_145
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9NAEF6l4QIcgAKivLQS3CyjdfzKHjhEKCVUdRE0rXqr1vugETSpaltC_Bn-KjO760dbhAAfrMSyndXOl9nZeXxDyOspy5QBcYYJj0yYqESFfGJUGKlUJ2pquDIY0S0OssVRsneSnoxGPwdZS01dvpE_fltX8j9ShWsgV6yS_QfJdi-FC_AZ5AtnkDCcrxm_V92sjlfA9mNofXkfhtSaNh3TN6brXCi-DGMhVkb75QoTcWw0_1Oz_r7qFPT7xoVjmj5dZ9VYB7poH_SNhYoCTFBM70KqxZkSFz530SUioE27vGyQdhbM2t0VGJrhR6T6DI6Xh3aQ8yKYffuygXGenduEx8-bsqnq4PBCa3mGNq3LbvLYwUnV1dt9H_c42NQ2nSxoW1O0muqKKyO95spoXZnBH5i-vKcqRia-gd6GC5MQtkZOV2qnyzNkaIwdI6rXz9x1rvFLPXfd6W6sIi5xBGxljrtX2B2lW2QrnyZjcms239s_7px4DHkEpv3Sj2yMLmzlRuOLiexoPcFYP3pfhoGFnMOfuhGSt5bO8j65i9UvFMtSYEIfkJFeb5N77QRTP8Hb5M6AyBK-FR37b_WQfAVc0A4XtMcFtbigcCvtcEEHuKCACwq4oPOCdriggAvqcEEdLugAF4_I0e58-W4R-qYeYYW9WGHZl4mUkzxKRZ6zMjWwI4k5y_EoY1VKsCeFEBPDRKZkygzLhDQRPMKZgM15_JiM15u1fkJoySWLNOznWSqTaWRKHmdSxmWJXjo4dsirdiZP8W9anbYc3cP5fvpXdz0jt3vEPifj-rLRL8AcrcuXHhS_AJFjhCA
linkProvider Library Specific Holdings
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=bookitem&rft.title=Computational+Intelligence+and+Security&rft.au=Shen%2C+Haifeng&rft.au=Li%2C+Qunxia&rft.au=Guo%2C+Jun&rft.au=Liu%2C+Gang&rft.atitle=HMM+Parameter+Adaptation+Using+the+Truncated+First-Order+VTS+and+EM+Algorithm+for+Robust+Speech+Recognition&rft.series=Lecture+Notes+in+Computer+Science&rft.date=2005-01-01&rft.pub=Springer+Berlin+Heidelberg&rft.isbn=9783540308188&rft.issn=0302-9743&rft.eissn=1611-3349&rft.spage=979&rft.epage=984&rft_id=info:doi/10.1007%2F11596448_145
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0302-9743&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0302-9743&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0302-9743&client=summon