File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: An Environment-Compensated Minimum Classification Error Training Approach Based on Stochastic Vector Mapping

TitleAn Environment-Compensated Minimum Classification Error Training Approach Based on Stochastic Vector Mapping
Authors
KeywordsFeature compensation
hidden Markov model (HMM)
minimum classification error training (MCE)
noise robustness
robust speech recognition
Issue Date2006
PublisherIEEE.
Citation
IEEE Transactions on Audio, Speech and Language Processing, 2006, v. 14 n. 6, p. 2147-2155 How to Cite?
AbstractA conventional feature compensation module for robust automatic speech recognition is usually designed separately from the training of hidden Markov model (HMM) parameters of the recognizer, albeit a maximum-likelihood (ML) criterion might be used in both designs. In this paper, we present an environment-compensated minimum classification error (MCE) training approach for the joint design of the feature compensation module and the recognizer itself. The feature compensation module is based on a stochastic vector mapping function whose parameters have to be learned from stereo data in a previous approach called SPLICE. In our proposed MCE joint design approach, by initializing the parameters with an approximate ML training procedure, the requirement of stereo data can be removed. By evaluating the proposed approach on Aurora2 connected digits database, a digit recognition error rate, averaged on all three test sets, of 5.66% is achieved for multicondition training. In comparison with the performance achieved by the baseline system using ETSI advanced front-end, our approach achieves an additional overall error rate reduction of 12.4%.
Persistent Identifierhttp://hdl.handle.net/10722/47081
ISSN
2015 Impact Factor: 1.877
2015 SCImago Journal Rankings: 1.963
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorWu, Jen_HK
dc.contributor.authorHuo, Qen_HK
dc.date.accessioned2007-10-30T07:06:40Z-
dc.date.available2007-10-30T07:06:40Z-
dc.date.issued2006en_HK
dc.identifier.citationIEEE Transactions on Audio, Speech and Language Processing, 2006, v. 14 n. 6, p. 2147-2155en_HK
dc.identifier.issn1558-7916en_HK
dc.identifier.urihttp://hdl.handle.net/10722/47081-
dc.description.abstractA conventional feature compensation module for robust automatic speech recognition is usually designed separately from the training of hidden Markov model (HMM) parameters of the recognizer, albeit a maximum-likelihood (ML) criterion might be used in both designs. In this paper, we present an environment-compensated minimum classification error (MCE) training approach for the joint design of the feature compensation module and the recognizer itself. The feature compensation module is based on a stochastic vector mapping function whose parameters have to be learned from stereo data in a previous approach called SPLICE. In our proposed MCE joint design approach, by initializing the parameters with an approximate ML training procedure, the requirement of stereo data can be removed. By evaluating the proposed approach on Aurora2 connected digits database, a digit recognition error rate, averaged on all three test sets, of 5.66% is achieved for multicondition training. In comparison with the performance achieved by the baseline system using ETSI advanced front-end, our approach achieves an additional overall error rate reduction of 12.4%.en_HK
dc.format.extent381071 bytes-
dc.format.extent1826 bytes-
dc.format.extent7254 bytes-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypetext/plain-
dc.format.mimetypetext/plain-
dc.languageengen_HK
dc.publisherIEEE.en_HK
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.rights©2006 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.en_HK
dc.subjectFeature compensationen_HK
dc.subjecthidden Markov model (HMM)en_HK
dc.subjectminimum classification error training (MCE)en_HK
dc.subjectnoise robustnessen_HK
dc.subjectrobust speech recognitionen_HK
dc.titleAn Environment-Compensated Minimum Classification Error Training Approach Based on Stochastic Vector Mappingen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=1558-7916&volume=14&issue=6&spage=2147&epage=2155&date=2006&atitle=An+Environment-Compensated+Minimum+Classification+Error+Training+Approach+Based+on+Stochastic+Vector+Mappingen_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.doi10.1109/TASL.2006.872616en_HK
dc.identifier.scopuseid_2-s2.0-44849090158-
dc.identifier.isiWOS:000241567200025-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats