File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: A study on the use of bi-directional contextual dependence in Markov Random Field-based Acoustic Modelling for speech recognition

TitleA study on the use of bi-directional contextual dependence in Markov Random Field-based Acoustic Modelling for speech recognition
Authors
KeywordsAcoustics
Algorithms
Markov processes
Mathematical models
Parallel processing systems
Issue Date1996
PublisherAcademic Press. The Journal's web site is located at http://www.elsevier.com/locate/csl
Citation
Computer Speech and Language, 1996, v. 10 n. 2, p. 95-105 How to Cite?
AbstractIn this paper, by using the formulation of the missing-data problem, a general framework for statistical acoustic modelling of speech is presented. With the motivation of utilizing bi-directional contextual dependence in acoustic modelling, a bi-directional hidden Markov modelling approach for speech recognition is studied and the importance of the bi-directional contextual dependence for speech recognition is identified by a series of comparative experiments. Furthermore, hidden Markov random field (MRF)-based acoustic modelling techniques using our previously proposed contextual vector quantization (CVQ) method and iterated conditional modes (ICM) algorithm, which is very suitable for parallel processing implementation, are also attempted. Their viability is confirmed by a series of preliminary experiments in a speaker-independent isolated English letter recognition task.
Persistent Identifierhttp://hdl.handle.net/10722/224735
ISSN
2015 Impact Factor: 1.324
2015 SCImago Journal Rankings: 0.974

 

DC FieldValueLanguage
dc.contributor.authorHuo, Q-
dc.contributor.authorChan, C-
dc.date.accessioned2016-04-13T08:18:51Z-
dc.date.available2016-04-13T08:18:51Z-
dc.date.issued1996-
dc.identifier.citationComputer Speech and Language, 1996, v. 10 n. 2, p. 95-105-
dc.identifier.issn0885-2308-
dc.identifier.urihttp://hdl.handle.net/10722/224735-
dc.description.abstractIn this paper, by using the formulation of the missing-data problem, a general framework for statistical acoustic modelling of speech is presented. With the motivation of utilizing bi-directional contextual dependence in acoustic modelling, a bi-directional hidden Markov modelling approach for speech recognition is studied and the importance of the bi-directional contextual dependence for speech recognition is identified by a series of comparative experiments. Furthermore, hidden Markov random field (MRF)-based acoustic modelling techniques using our previously proposed contextual vector quantization (CVQ) method and iterated conditional modes (ICM) algorithm, which is very suitable for parallel processing implementation, are also attempted. Their viability is confirmed by a series of preliminary experiments in a speaker-independent isolated English letter recognition task.-
dc.languageeng-
dc.publisherAcademic Press. The Journal's web site is located at http://www.elsevier.com/locate/csl-
dc.relation.ispartofComputer Speech and Language-
dc.rightsPosting accepted manuscript (postprint): © <year>. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/-
dc.subjectAcoustics-
dc.subjectAlgorithms-
dc.subjectMarkov processes-
dc.subjectMathematical models-
dc.subjectParallel processing systems-
dc.titleA study on the use of bi-directional contextual dependence in Markov Random Field-based Acoustic Modelling for speech recognition-
dc.typeArticle-
dc.identifier.emailHuo, Q: qhuo@itl.atr.co.jp-
dc.identifier.emailChan, C: cchan@cs.hku.hk-
dc.identifier.doi10.1006/csla.1996.0006-
dc.identifier.scopuseid_2-s2.0-0030121298-
dc.identifier.hkuros20955-
dc.identifier.volume10-
dc.identifier.issue2-
dc.identifier.spage95-
dc.identifier.epage105-
dc.publisher.placeUnited Kingdom-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats