File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Integrated approaches to prosodic word prediction for Chinese TTS

TitleIntegrated approaches to prosodic word prediction for Chinese TTS
Authors
KeywordsProsodic word prediction
Test-to-speech synthesis
Lexicalized HMMs
Issue Date2003
PublisherIEEE.
Citation
International Conference on Natural Language Processing and Knowledge Engineering Proceedings, Beijing, China, 26-29 October 2003, p. 413-418 How to Cite?
AbstractWe focus on integrated prosodic word prediction for Chinese TTS. To avoid the problem of inconsistency between lexical words and prosodic words in Chinese, lexical word segmentation and prosodic word prediction are taken as one process instead of two independent tasks. Furthermore, two word-based approaches are proposed to drive this integrated prosodic word prediction: The first one follows the notion of lexicalized hidden Markov models, and the second one is borrowed from unknown word identification for Chinese. The results of our primary experiment show these integrated approaches are effective.
Persistent Identifierhttp://hdl.handle.net/10722/47019

 

DC FieldValueLanguage
dc.contributor.authorFu, Gen_HK
dc.contributor.authorLuke, KKen_HK
dc.date.accessioned2007-10-30T07:04:22Z-
dc.date.available2007-10-30T07:04:22Z-
dc.date.issued2003en_HK
dc.identifier.citationInternational Conference on Natural Language Processing and Knowledge Engineering Proceedings, Beijing, China, 26-29 October 2003, p. 413-418en_HK
dc.identifier.urihttp://hdl.handle.net/10722/47019-
dc.description.abstractWe focus on integrated prosodic word prediction for Chinese TTS. To avoid the problem of inconsistency between lexical words and prosodic words in Chinese, lexical word segmentation and prosodic word prediction are taken as one process instead of two independent tasks. Furthermore, two word-based approaches are proposed to drive this integrated prosodic word prediction: The first one follows the notion of lexicalized hidden Markov models, and the second one is borrowed from unknown word identification for Chinese. The results of our primary experiment show these integrated approaches are effective.en_HK
dc.format.extent357170 bytes-
dc.format.extent2213 bytes-
dc.format.mimetypeapplication/pdf-
dc.format.mimetypetext/plain-
dc.languageengen_HK
dc.publisherIEEE.en_HK
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.rights©2003 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.subjectProsodic word predictionen_HK
dc.subjectTest-to-speech synthesisen_HK
dc.subjectLexicalized HMMsen_HK
dc.titleIntegrated approaches to prosodic word prediction for Chinese TTSen_HK
dc.typeConference_Paperen_HK
dc.description.naturepublished_or_final_versionen_HK
dc.identifier.doi10.1109/NLPKE.2003.1275941en_HK
dc.identifier.hkuros103506-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats