File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Unsupervised Online Adaptation of Segmental Switching Linear Gaussian Hidden Markov Models for Robust Speech Recognition

TitleUnsupervised Online Adaptation of Segmental Switching Linear Gaussian Hidden Markov Models for Robust Speech Recognition
Authors
KeywordsEngineering
Electrical engineering
Issue Date2006
PublisherIEEE.
Citation
IEEE International Conference on Acoustics, Speech and Signal Processing Proceedings, Toulouse, France, 14-19 May 2006, v. 1, p. 1125-1128 How to Cite?
AbstractIn our previous works, a Segmental Switching Linear Gaussian Hidden Markov Model (SSLGHMM) was proposed to model 'noisy' speech utterance for robust speech recognition. Both ML (maximum likelihood) and MCE (minimum classification error) training procedures were developed for training model parameters and their effectiveness was confirmed by evaluation experiments on Aurora2 and Aurora3 databases. In this paper, we present an ML approach to unsupervised online adaptation (OLA) of SSLGHMM parameters for achieving further performance improvement. An important implementation issue of how to initialize the switching linear Gaussian model parameters is also studied. Evaluation results on Finnish Aurora3 database show that in comparison with the performance of a baseline system based on ML-trained SSLGHMMs, unsupervised OLA yields a relative word error rate reduction of 4.3%, 9.1%, and 17.8% for well-matched, medium-mismatched, and high-mismatched conditions respectively.
Persistent Identifierhttp://hdl.handle.net/10722/45562
ISSN

 

DC FieldValueLanguage
dc.contributor.authorHuo, Qen_HK
dc.contributor.authorZhu, Den_HK
dc.contributor.authorWu, Jen_HK
dc.date.accessioned2007-10-30T06:29:13Z-
dc.date.available2007-10-30T06:29:13Z-
dc.date.issued2006en_HK
dc.identifier.citationIEEE International Conference on Acoustics, Speech and Signal Processing Proceedings, Toulouse, France, 14-19 May 2006, v. 1, p. 1125-1128en_HK
dc.identifier.issn1520-6149en_HK
dc.identifier.urihttp://hdl.handle.net/10722/45562-
dc.description.abstractIn our previous works, a Segmental Switching Linear Gaussian Hidden Markov Model (SSLGHMM) was proposed to model 'noisy' speech utterance for robust speech recognition. Both ML (maximum likelihood) and MCE (minimum classification error) training procedures were developed for training model parameters and their effectiveness was confirmed by evaluation experiments on Aurora2 and Aurora3 databases. In this paper, we present an ML approach to unsupervised online adaptation (OLA) of SSLGHMM parameters for achieving further performance improvement. An important implementation issue of how to initialize the switching linear Gaussian model parameters is also studied. Evaluation results on Finnish Aurora3 database show that in comparison with the performance of a baseline system based on ML-trained SSLGHMMs, unsupervised OLA yields a relative word error rate reduction of 4.3%, 9.1%, and 17.8% for well-matched, medium-mismatched, and high-mismatched conditions respectively.en_HK
dc.format.extent129456 bytes-
dc.format.extent2385 bytes-
dc.format.extent1861 bytes-
dc.format.extent7254 bytes-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypetext/plain-
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.subjectEngineeringen_HK
dc.subjectElectrical engineeringen_HK
dc.titleUnsupervised Online Adaptation of Segmental Switching Linear Gaussian Hidden Markov Models for Robust Speech Recognitionen_HK
dc.typeConference_Paperen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=1520-6149&volume=1&spage=1125&epage=1128&date=2006&atitle=Unsupervised+Online+Adaptation+of+Segmental+Switching+Linear+Gaussian+Hidden+Markov+Models+for+Robust+Speech+Recognitionen_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.doi10.1109/ICASSP.2006.1660223en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats