File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Irrelevant variability normalization in learning HMM state tying from data based on phonetic decision-tree

TitleIrrelevant variability normalization in learning HMM state tying from data based on phonetic decision-tree
Authors
KeywordsEngineering
Electrical engineering
Issue Date1999
PublisherIEEE.
Citation
IEEE International Conference on Acoustics, Speech and Signal Processing Proceedings, Phoenix, Arizona, USA, 15-19 March 1999, v. 2, p. 577-580 How to Cite?
AbstractWe propose to apply the concept of irrelevant variability normalization to the general problem of learning structure from data. Because of the problems of a diversified training data set and/or possible acoustic mismatches between training and testing conditions, the structure learned from the training data by using a maximum likelihood training method will not necessarily generalize well on mismatched tasks. We apply the above concept to the structural learning problem of phonetic decision-tree based hidden Markov model (HMM) state tying. We present a new method that integrates a linear-transformation based normalization mechanism into the decision-tree construction process to make the learned structure have a better modeling capability and generalizability. The viability and efficacy of the proposed method are confirmed in a series of experiments for continuous speech recognition of Mandarin Chinese.
Persistent Identifierhttp://hdl.handle.net/10722/45609
ISSN

 

DC FieldValueLanguage
dc.contributor.authorHuo, Qen_HK
dc.contributor.authorMa, Ben_HK
dc.date.accessioned2007-10-30T06:30:13Z-
dc.date.available2007-10-30T06:30:13Z-
dc.date.issued1999en_HK
dc.identifier.citationIEEE International Conference on Acoustics, Speech and Signal Processing Proceedings, Phoenix, Arizona, USA, 15-19 March 1999, v. 2, p. 577-580en_HK
dc.identifier.issn1520-6149en_HK
dc.identifier.urihttp://hdl.handle.net/10722/45609-
dc.description.abstractWe propose to apply the concept of irrelevant variability normalization to the general problem of learning structure from data. Because of the problems of a diversified training data set and/or possible acoustic mismatches between training and testing conditions, the structure learned from the training data by using a maximum likelihood training method will not necessarily generalize well on mismatched tasks. We apply the above concept to the structural learning problem of phonetic decision-tree based hidden Markov model (HMM) state tying. We present a new method that integrates a linear-transformation based normalization mechanism into the decision-tree construction process to make the learned structure have a better modeling capability and generalizability. The viability and efficacy of the proposed method are confirmed in a series of experiments for continuous speech recognition of Mandarin Chinese.en_HK
dc.format.extent447881 bytes-
dc.format.extent7254 bytes-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypetext/plain-
dc.languageengen_HK
dc.publisherIEEE.en_HK
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.rights©1999 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.titleIrrelevant variability normalization in learning HMM state tying from data based on phonetic decision-treeen_HK
dc.typeConference_Paperen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=1520-6149&volume=2&spage=577&epage=580&date=1999&atitle=Irrelevant+variability+normalization+in+learning+HMM+state+tying+from+data+based+on+phonetic+decision-treeen_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.doi10.1109/ICASSP.1999.759732en_HK
dc.identifier.hkuros42212-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats