Robust MVDR-based feature extraction for speech recognition

This paper presents a novel noise robust feature extraction method for speech recognition. It is based on making the Minimum Variance Distortionless Response (MVDR) power spectrum estimation method robust against noise. This robustness is obtained by modifying the distortionless constraint of the MV...

Full description

Saved in:
Bibliographic Details
Published in2009 7th International Conference on Information, Communications and Signal Processing pp. 1 - 5
Main Authors Seyedin, S., Ahadi, S.M.
Format Conference Proceeding
LanguageEnglish
Japanese
Published IEEE 01.12.2009
Subjects
Distortion
Feature extraction
Finite impulse response filter
Mel frequency cepstral coefficient
Noise robustness
Power generation
robust MVDR power spectral estimation
Signal to noise ratio
Spectral analysis
Speech recognition
Working environment noise
Online AccessGet full text
ISBN9781424446568
1424446562
DOI10.1109/ICICS.2009.5397503

Cover

Abstract This paper presents a novel noise robust feature extraction method for speech recognition. It is based on making the Minimum Variance Distortionless Response (MVDR) power spectrum estimation method robust against noise. This robustness is obtained by modifying the distortionless constraint of the MVDR spectral estimation method via weighting the subband power spectrum values based on the sub-band signal to noise ratios. The above method, when evaluated on Aurora 2 task, outperformed both the MFCC features as the baseline and the MVDR-based features in different noisy conditions.
AbstractList This paper presents a novel noise robust feature extraction method for speech recognition. It is based on making the Minimum Variance Distortionless Response (MVDR) power spectrum estimation method robust against noise. This robustness is obtained by modifying the distortionless constraint of the MVDR spectral estimation method via weighting the subband power spectrum values based on the sub-band signal to noise ratios. The above method, when evaluated on Aurora 2 task, outperformed both the MFCC features as the baseline and the MVDR-based features in different noisy conditions.
Author Ahadi, S.M.
Seyedin, S.
Author_xml – sequence: 1
  givenname: S.
  surname: Seyedin
  fullname: Seyedin, S.
  organization: Electr. Eng. Dept., Amirkabir Univ. of Technol., Tehran, Iran
– sequence: 2
  givenname: S.M.
  surname: Ahadi
  fullname: Ahadi, S.M.
  organization: Electr. Eng. Dept., Amirkabir Univ. of Technol., Tehran, Iran
BookMark eNpVT8lKA0EUbNGAJs4P6KV_YOLr5fWCJxm3gYgQl2uY5bWO6EzonoD-vQnmYl2KKoqiasqO-qEnxs4EzIUAf1EWZfE0lwB-jspbBHXAMm-d0FJrbdDi4T9t3IRNd3EP2lh_zLKUPmALjdJZfcIul0O9SSN_eL1e5nWVqOWBqnETidP3GKtm7IaehyHytCZq3nmkZnjru519yiah-kyU7XnGXm5vnov7fPF4VxZXi7wTaMZc1CgRXQ3U1gZss90mIOigECmY4BujPRrVGieNktpbEg6NRwJoZCtJzdj5X29HRKt17L6q-LPa_1e_Di1MOQ
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICICS.2009.5397503
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9781424446575
1424446570
EndPage 5
ExternalDocumentID 5397503
Genre orig-research
GroupedDBID 6IE
6IF
6IG
6IK
6IL
6IM
6IN
AAJGR
AARBI
AAWTH
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
IERZE
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-i156t-1b52558b0edb607c14210f4f355ef6f9c649563d682632497e185695e00c2d2e3
IEDL.DBID RIE
ISBN 9781424446568
1424446562
IngestDate Wed Aug 27 02:58:11 EDT 2025
IsPeerReviewed false
IsScholarly false
LCCN 2009904679
Language English
Japanese
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i156t-1b52558b0edb607c14210f4f355ef6f9c649563d682632497e185695e00c2d2e3
PageCount 5
ParticipantIDs ieee_primary_5397503
PublicationCentury 2000
PublicationDate 2009-12
PublicationDateYYYYMMDD 2009-12-01
PublicationDate_xml – month: 12
  year: 2009
  text: 2009-12
PublicationDecade 2000
PublicationTitle 2009 7th International Conference on Information, Communications and Signal Processing
PublicationTitleAbbrev ICICS
PublicationYear 2009
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0000452874
Score 1.4510654
Snippet This paper presents a novel noise robust feature extraction method for speech recognition. It is based on making the Minimum Variance Distortionless Response...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Distortion
Feature extraction
Finite impulse response filter
Mel frequency cepstral coefficient
Noise robustness
Power generation
robust MVDR power spectral estimation
Signal to noise ratio
Spectral analysis
Speech recognition
Working environment noise
Title Robust MVDR-based feature extraction for speech recognition
URI https://ieeexplore.ieee.org/document/5397503
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV09T8MwELVKJyZALeJbHhhJ67i244gxULVIRahQ1K2q7bNASEnVJgu_HjtfCMTA5niIzo6Ud8--9w6ha7ImkeXMBoKGOmDWiEBK7sgKVUJRTn2nSV9t8SgmC_aw5MsOumm1MABQFp_BwA_Lu3yT6cIflQ25A0_urT33IikqrVZ7nuKtwWXEGu2WtwGjjaVT_Swb0QyJh9NkmjxXdpX1W3-0VynRZXyAZk1cVVHJx6DI1UB__rJs_G_gh6j_rePDTy1CHaEOpD10O89Uscvx7PVuHngQM9hCae-J3Y96WwkdsMtl8W4DoN9wW2OUpX20GN-_JJOgbqEQvDtilgeh4o4zSEXAKEEi7fYiJJZZl2WAFTbWwhOkkRGy9G2PI3D4LWIOhGhqKIyOUTfNUjhB2CiXDMaODso1YaHU0mgbrZl2KYBxTFeeop5f-GpTuWSs6jWf_T19jvZp3YmBhBeom28LuHTwnqur8rt-AeL7nhE
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV27TsMwFLUqGGAC1CLeeGDErePajiPGQtVCW6HSom5V_RIIKanaZOHrsfNCIAY2x0N07Ug599j3nAvADV7h0DJqESeBQtRqjoRgjqwQySVhxHea9NUWEz6Y08cFWzTAba2FMcbkxWem7Yf5Xb5OVOaPyjrMgSfz1p67jFLKCrVWfaLizcFFSCv1ljcCI5WpU_ksKtkMjjrD3rD3UhhWlu_90WAlx5f-ARhXkRVlJR_tLJVt9fnLtPG_oR-C1reSDz7XGHUEGiZugrtpIrNtCsev91PkYUxDa3KDT-h-1ZtC6gBdNgu3a2PUG6yrjJK4Beb9h1lvgMomCujdUbMUBZI51iAkNlpyHCq3FwG21Lo8w1huI8U9RepqLnLn9ig0DsF5xAzGimhiusdgJ05icwKgli4djBwhFCtMA6GEVjZcUeWSAO24rjgFTb_w5brwyViWaz77e_oa7A1m49FyNJw8nYN9UvZlwMEF2Ek3mbl0YJ_Kq_wbfwFi96Fe
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=proceeding&rft.title=2009+7th+International+Conference+on+Information%2C+Communications+and+Signal+Processing&rft.atitle=Robust+MVDR-based+feature+extraction+for+speech+recognition&rft.au=Seyedin%2C+S.&rft.au=Ahadi%2C+S.M.&rft.date=2009-12-01&rft.pub=IEEE&rft.isbn=9781424446568&rft.spage=1&rft.epage=5&rft_id=info:doi/10.1109%2FICICS.2009.5397503&rft.externalDocID=5397503
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9781424446568/lc.gif&client=summon&freeimage=true
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9781424446568/mc.gif&client=summon&freeimage=true
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9781424446568/sc.gif&client=summon&freeimage=true