File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Efficient ML training of CDHMM parameters based on prior evolution,posterior intervention and feedback

TitleEfficient ML training of CDHMM parameters based on prior evolution,posterior intervention and feedback
Authors
KeywordsEngineering
Electrical engineering
Issue Date2000
PublisherIEEE.
Citation
IEEE International Conference on Acoustics, Speech and Signal Processing Proceedings, Istanbul, Turkey, 5-9 June 2000, v. 2, p. II1001-II1004 How to Cite?
AbstractWe present an efficient maximum likelihood (ML) training procedure for Gaussian mixture continuous density hidden Markov model (CDHMM) parameters. This procedure is proposed using the concept of approximate prior evolution, posterior intervention and feedback (PEPIF). In a series of experiments for training CDHMMs for a continuous Mandarin Chinese speech recognition task, the new PEPIF procedure achieves a 4-fold speed-up in terms of user CPU time over that of the Baum-Welch algorithm in producing models of given likelihood or recognition accuracy.
Persistent Identifierhttp://hdl.handle.net/10722/45611
ISSN

 

DC FieldValueLanguage
dc.contributor.authorHuo, Qen_HK
dc.contributor.authorSmith, NDen_HK
dc.contributor.authorMa, Ben_HK
dc.date.accessioned2007-10-30T06:30:15Z-
dc.date.available2007-10-30T06:30:15Z-
dc.date.issued2000en_HK
dc.identifier.citationIEEE International Conference on Acoustics, Speech and Signal Processing Proceedings, Istanbul, Turkey, 5-9 June 2000, v. 2, p. II1001-II1004en_HK
dc.identifier.issn1520-6149en_HK
dc.identifier.urihttp://hdl.handle.net/10722/45611-
dc.description.abstractWe present an efficient maximum likelihood (ML) training procedure for Gaussian mixture continuous density hidden Markov model (CDHMM) parameters. This procedure is proposed using the concept of approximate prior evolution, posterior intervention and feedback (PEPIF). In a series of experiments for training CDHMMs for a continuous Mandarin Chinese speech recognition task, the new PEPIF procedure achieves a 4-fold speed-up in terms of user CPU time over that of the Baum-Welch algorithm in producing models of given likelihood or recognition accuracy.en_HK
dc.format.extent445846 bytes-
dc.format.extent7254 bytes-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypetext/plain-
dc.languageengen_HK
dc.publisherIEEE.en_HK
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.rights©2000 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.subjectEngineeringen_HK
dc.subjectElectrical engineeringen_HK
dc.titleEfficient ML training of CDHMM parameters based on prior evolution,posterior intervention and feedbacken_HK
dc.typeConference_Paperen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=1520-6149&volume=2&spage=II1001&epage=II1004&date=2000&atitle=Efficient+ML+training+of+CDHMM+parameters+based+on+prior+evolution,posterior+intervention+and+feedbacken_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.doi10.1109/ICASSP.2000.859131en_HK
dc.identifier.hkuros50353-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats