N-gram adaptation with dynamic interpolation coefficient using information retrieval technique

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 760
  • Download : 547
DC FieldValueLanguage
dc.contributor.authorChoi, JKko
dc.contributor.authorOh, Yung-Hwanko
dc.date.accessioned2010-03-22T09:01:52Z-
dc.date.available2010-03-22T09:01:52Z-
dc.date.created2012-02-06-
dc.date.created2012-02-06-
dc.date.issued2006-09-
dc.identifier.citationIEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, v.E89D, no.9, pp.2579 - 2582-
dc.identifier.issn0916-8532-
dc.identifier.urihttp://hdl.handle.net/10203/17279-
dc.description.abstractThis study presents an N-gram adaptation technique when additional text data for the adaptation do not exist. We use a language modeling approach to the information retrieval (IR) technique to collect the appropriate adaptation corpus from baseline text data. We propose to use a dynamic interpolation coefficient to merge the N-gram, where the interpolation coefficient is estimated from the word hypotheses obtained by segmenting the input speech. Experimental results show that the proposed adapted N-gram always has better performance than the background N-gram.-
dc.languageEnglish-
dc.language.isoen_USen
dc.publisherIEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG-
dc.titleN-gram adaptation with dynamic interpolation coefficient using information retrieval technique-
dc.typeArticle-
dc.identifier.wosid000240524000012-
dc.identifier.scopusid2-s2.0-33748796627-
dc.type.rimsART-
dc.citation.volumeE89D-
dc.citation.issue9-
dc.citation.beginningpage2579-
dc.citation.endingpage2582-
dc.citation.publicationnameIEICE TRANSACTIONS ON INFORMATION AND SYSTEMS-
dc.identifier.doi10.1093/ietisy/e89-d.9.2579-
dc.contributor.localauthorOh, Yung-Hwan-
dc.contributor.nonIdAuthorChoi, JK-
dc.type.journalArticleArticle-
dc.subject.keywordAuthorlanguage model adaptation-
dc.subject.keywordAuthoradaptation corpus-
dc.subject.keywordAuthordynamic interpolation coefficient-
dc.subject.keywordAuthorspeech recognition-

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0