File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: A study of switching state segmentation in segmental switching linear Gaussian hidden Markov models for robust speech recognition

TitleA study of switching state segmentation in segmental switching linear Gaussian hidden Markov models for robust speech recognition
Authors
Issue Date2004
PublisherIEEE, Signal Processing Society.
Citation
The 4th International Symposium on Chinese Spoken Language Processing, Hong Kong, China, 15-18 December 2004, p. 97-100 How to Cite?
AbstractIn our previous works, a switching linear Gaussian hidden Markov model (SLGHMM) and its segmental derivative, SSLGHMM, were proposed to cast the problem of modeling a noisy speech utterance in robust automatic speech recognition by a well-designed dynamic Bayesian network. An important issue of SSLGHMM is how to specify a switching state value for each frame of the feature vector in a given speech utterance. In this paper, we propose several approaches for addressing this issue and compare their performance on Aurora3 connected digit recognition tasks.
Persistent Identifierhttp://hdl.handle.net/10722/45526

 

DC FieldValueLanguage
dc.contributor.authorZhu, Den_HK
dc.contributor.authorHuo, Qen_HK
dc.contributor.authorWu, Jen_HK
dc.date.accessioned2007-10-30T06:28:28Z-
dc.date.available2007-10-30T06:28:28Z-
dc.date.issued2004en_HK
dc.identifier.citationThe 4th International Symposium on Chinese Spoken Language Processing, Hong Kong, China, 15-18 December 2004, p. 97-100en_HK
dc.identifier.urihttp://hdl.handle.net/10722/45526-
dc.description.abstractIn our previous works, a switching linear Gaussian hidden Markov model (SLGHMM) and its segmental derivative, SSLGHMM, were proposed to cast the problem of modeling a noisy speech utterance in robust automatic speech recognition by a well-designed dynamic Bayesian network. An important issue of SSLGHMM is how to specify a switching state value for each frame of the feature vector in a given speech utterance. In this paper, we propose several approaches for addressing this issue and compare their performance on Aurora3 connected digit recognition tasks.en_HK
dc.format.extent323608 bytes-
dc.format.extent2385 bytes-
dc.format.extent7254 bytes-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypetext/plain-
dc.format.mimetypetext/plain-
dc.languageengen_HK
dc.publisherIEEE, Signal Processing Society.en_HK
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.titleA study of switching state segmentation in segmental switching linear Gaussian hidden Markov models for robust speech recognitionen_HK
dc.typeConference_Paperen_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.doi10.1109/CHINSL.2004.1409595en_HK
dc.identifier.hkuros101975-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats