File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: On adaptive decision rules and decision parameter adaptation for automatic speech recognition

TitleOn adaptive decision rules and decision parameter adaptation for automatic speech recognition
Authors
KeywordsAcoustic modeling
Adaptive decision rule
Automatic speech recognition
Bayes’ predictive classification rule
Bayes’ risk consistency
Issue Date2000
PublisherIEEE.
Citation
Institute of Electrical and Electronics Engineers Proceedings, 2000, v. 88 n. 8, p. 1241-1269 How to Cite?
AbstractRecent advances in automatic speech recognition are accomplished by designing a plug-in maximum a posteriori decision rule such that the forms of the acoustic and language model distributions are specified and the parameters of the assumed distributions are estimated from a collection of speech and language training corpora. Maximum-likelihood point estimation is by far the most prevailing training method. However, due to the problems of unknown speech distributions, sparse training data, high spectral and temporal variabilities in speech, and possible mismatch between training and testing conditions, a dynamic training strategy is needed. To cope with the changing speakers and speaking conditions in real operational conditions for high-performance speech recognition, such paradigms incorporate a small amount of speaker and environment specific adaptation data into the training process. Bayesian adaptive learning is an optimal way to combine prior knowledge in an existing collection of general models with a new set of condition-specific adaptation data. In this paper, the mathematical framework for Bayesian adaptation of acoustic and language model parameters is first described. Maximum a posteriori point estimation is then developed for hidden Markov models and a number of useful parameters densities commonly used in automatic speech recognition and natural language processing.
Persistent Identifierhttp://hdl.handle.net/10722/43653
ISSN
2015 Impact Factor: 5.629
2015 SCImago Journal Rankings: 1.586

 

DC FieldValueLanguage
dc.contributor.authorLee, CHen_HK
dc.contributor.authorHuo, Qen_HK
dc.date.accessioned2007-03-23T04:51:19Z-
dc.date.available2007-03-23T04:51:19Z-
dc.date.issued2000en_HK
dc.identifier.citationInstitute of Electrical and Electronics Engineers Proceedings, 2000, v. 88 n. 8, p. 1241-1269en_HK
dc.identifier.issn0018-9219en_HK
dc.identifier.urihttp://hdl.handle.net/10722/43653-
dc.description.abstractRecent advances in automatic speech recognition are accomplished by designing a plug-in maximum a posteriori decision rule such that the forms of the acoustic and language model distributions are specified and the parameters of the assumed distributions are estimated from a collection of speech and language training corpora. Maximum-likelihood point estimation is by far the most prevailing training method. However, due to the problems of unknown speech distributions, sparse training data, high spectral and temporal variabilities in speech, and possible mismatch between training and testing conditions, a dynamic training strategy is needed. To cope with the changing speakers and speaking conditions in real operational conditions for high-performance speech recognition, such paradigms incorporate a small amount of speaker and environment specific adaptation data into the training process. Bayesian adaptive learning is an optimal way to combine prior knowledge in an existing collection of general models with a new set of condition-specific adaptation data. In this paper, the mathematical framework for Bayesian adaptation of acoustic and language model parameters is first described. Maximum a posteriori point estimation is then developed for hidden Markov models and a number of useful parameters densities commonly used in automatic speech recognition and natural language processing.en_HK
dc.format.extent536481 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©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.subjectAcoustic modelingen_HK
dc.subjectAdaptive decision ruleen_HK
dc.subjectAutomatic speech recognitionen_HK
dc.subjectBayes’ predictive classification ruleen_HK
dc.subjectBayes’ risk consistencyen_HK
dc.titleOn adaptive decision rules and decision parameter adaptation for automatic speech recognitionen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=0018-9219&volume=88&issue=8&spage=1241&epage=1269&date=2000&atitle=On+adaptive+decision+rules+and+decision+parameter+adaptation+for+automatic+speech+recognitionen_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.doi10.1109/5.880082en_HK
dc.identifier.scopuseid_2-s2.0-0000159105-
dc.identifier.hkuros57630-
dc.identifier.citeulike6089340-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats