File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: A Bayesian predictive classification approach to robust speech recognition

TitleA Bayesian predictive classification approach to robust speech recognition
Authors
KeywordsEngineering
Electrical engineering
Issue Date1997
PublisherIEEE.
Citation
IEEE International Conference on Acoustics, Speech and Signal Processing Proceedings, Munich, Germany, 21-24 April 1997, v. 2, p. 1547-1550 How to Cite?
AbstractWe introduce a new Bayesian predictive classification (BPC) approach to robust speech recognition and apply the BPC framework to Gaussian mixture continuous density hidden Markov model based speech recognition. We propose and focus on one of the approximate BPC approaches called quasi-Bayesian predictive classification (QBPC). In comparison with the standard plug-in maximum a posteriori decoding, when the QBPC method is applied to speaker independent recognition of a confusable vocabulary namely 26 English letters, where a broad range of mismatches between training and testing conditions exist, the QBPC achieves around 14% relative recognition error rate reduction. While the QBPC method is applied to cross-gender testing on a less confusable vocabulary, namely 20 English digits and commands, the QBPC method achieves around 24% relative recognition error rate reduction.
Persistent Identifierhttp://hdl.handle.net/10722/45586
ISSN

 

DC FieldValueLanguage
dc.contributor.authorHuo, Qen_HK
dc.contributor.authorJiang, Hen_HK
dc.contributor.authorLee, CHen_HK
dc.date.accessioned2007-10-30T06:29:45Z-
dc.date.available2007-10-30T06:29:45Z-
dc.date.issued1997en_HK
dc.identifier.citationIEEE International Conference on Acoustics, Speech and Signal Processing Proceedings, Munich, Germany, 21-24 April 1997, v. 2, p. 1547-1550en_HK
dc.identifier.issn1520-6149en_HK
dc.identifier.urihttp://hdl.handle.net/10722/45586-
dc.description.abstractWe introduce a new Bayesian predictive classification (BPC) approach to robust speech recognition and apply the BPC framework to Gaussian mixture continuous density hidden Markov model based speech recognition. We propose and focus on one of the approximate BPC approaches called quasi-Bayesian predictive classification (QBPC). In comparison with the standard plug-in maximum a posteriori decoding, when the QBPC method is applied to speaker independent recognition of a confusable vocabulary namely 26 English letters, where a broad range of mismatches between training and testing conditions exist, the QBPC achieves around 14% relative recognition error rate reduction. While the QBPC method is applied to cross-gender testing on a less confusable vocabulary, namely 20 English digits and commands, the QBPC method achieves around 24% relative recognition error rate reduction.en_HK
dc.format.extent483849 bytes-
dc.format.extent7254 bytes-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypetext/plain-
dc.languageengen_HK
dc.publisherIEEE.en_HK
dc.rights©1997 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.-
dc.subjectEngineeringen_HK
dc.subjectElectrical engineeringen_HK
dc.titleA Bayesian predictive classification approach to robust speech recognitionen_HK
dc.typeConference_Paperen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=1520-6149&volume=2&spage=1547&epage=1550&date=1997&atitle=A+Bayesian+predictive+classification+approach+to+robust+speech+recognitionen_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.doi10.1109/ICASSP.1997.596246en_HK
dc.identifier.hkuros31111-
dc.identifier.issnl1520-6149-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats