File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Online adaptive learning of continuous-density hidden Markov models based on multiple-stream prior evolution and posterior pooling

TitleOnline adaptive learning of continuous-density hidden Markov models based on multiple-stream prior evolution and posterior pooling
Authors
Issue Date2001
PublisherIEEE.
Citation
IEEE Transactions on Speech and Audio Processing, 2001, v. 9 n. 4, p. 388-398 How to Cite?
AbstractWe introduce a new adaptive Bayesian learning framework, called multiple-stream prior evolution and posterior pooling, for online adaptation of the continuous density hidden Markov model (CDHMM) parameters. Among three architectures we proposed for this framework, we study in detail a specific two stream system where linear transformations are applied to the mean vectors of the CDHMMs to control the evolution of their prior distribution. This new stream of prior distribution can be combined with another stream of prior distribution evolved without any constraints applied. In a series of speaker adaptation experiments on the task of continuous Mandarin speech recognition, we show that the new adaptation algorithm achieves a similar fast-adaptation performance as that of the incremental maximum likelihood linear regression (MLLR) in the case of small amount of adaptation data, while maintains the good asymptotic convergence property as that of our previously proposed quasi-Bayes adaptation algorithms.
Persistent Identifierhttp://hdl.handle.net/10722/43655
ISSN
2007 Impact Factor: 2.291

 

DC FieldValueLanguage
dc.contributor.authorHuo, Qen_HK
dc.contributor.authorMa, Ben_HK
dc.date.accessioned2007-03-23T04:51:21Z-
dc.date.available2007-03-23T04:51:21Z-
dc.date.issued2001en_HK
dc.identifier.citationIEEE Transactions on Speech and Audio Processing, 2001, v. 9 n. 4, p. 388-398en_HK
dc.identifier.issn1063-6676en_HK
dc.identifier.urihttp://hdl.handle.net/10722/43655-
dc.description.abstractWe introduce a new adaptive Bayesian learning framework, called multiple-stream prior evolution and posterior pooling, for online adaptation of the continuous density hidden Markov model (CDHMM) parameters. Among three architectures we proposed for this framework, we study in detail a specific two stream system where linear transformations are applied to the mean vectors of the CDHMMs to control the evolution of their prior distribution. This new stream of prior distribution can be combined with another stream of prior distribution evolved without any constraints applied. In a series of speaker adaptation experiments on the task of continuous Mandarin speech recognition, we show that the new adaptation algorithm achieves a similar fast-adaptation performance as that of the incremental maximum likelihood linear regression (MLLR) in the case of small amount of adaptation data, while maintains the good asymptotic convergence property as that of our previously proposed quasi-Bayes adaptation algorithms.en_HK
dc.format.extent228429 bytes-
dc.format.extent27136 bytes-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypeapplication/msword-
dc.languageengen_HK
dc.publisherIEEE.en_HK
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.rights©2001 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.titleOnline adaptive learning of continuous-density hidden Markov models based on multiple-stream prior evolution and posterior poolingen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=1063-6676&volume=9&issue=4&spage=388&epage=398&date=2001&atitle=Online+adaptive+learning+of+continuous-density+hidden+Markov+models+based+on+multiple-stream+prior+evolution+and+posterior+poolingen_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.doi10.1109/89.917684en_HK
dc.identifier.scopuseid_2-s2.0-0035341099-
dc.identifier.hkuros57634-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats