このアイテムのアクセス数: 358

このアイテムのファイル:
ファイル 記述 サイズフォーマット 
TSA.2004.828641.pdf425.35 kBAdobe PDF見る/開く
完全メタデータレコード
DCフィールド言語
dc.contributor.authorNanjo, H.ja
dc.contributor.authorKawahara, T.ja
dc.contributor.alternative河原, 達也ja
dc.date.accessioned2010-10-21T01:56:07Z-
dc.date.available2010-10-21T01:56:07Z-
dc.date.issued2004-07-
dc.identifier.issn1063-6676ja
dc.identifier.urihttp://hdl.handle.net/2433/128905-
dc.description.abstractThe paper addresses adaptation methods to language model and speaking rate (SR) of individual speakers which are two major problems in automatic transcription of spontaneous presentation speech. To cope with a large variation in expression and pronunciation of words depending on the speaker, firstly, we investigate the effect of statistical and context-dependent pronunciation modeling. Secondly, we present unsupervised methods of language model adaptation to a specific speaker and a topic by 1) selecting similar texts based on the word perplexity and TF-IDF measure and 2) making direct use of the initial recognition result for generating an enhanced model. We confirm that all proposed adaptation methods and their combinations reduce the perplexity and word error rate. We also present a decoding strategy adapted to the SR. In spontaneous speech, SR is generally fast and may vary a lot. We also observe different error tendencies for portions of presentations where speech is fast or slow. Therefore, we propose a SR-dependent decoding strategy that applies the most appropriate acoustic analysis, phone models, and decoding parameters according to the SR. Several methods are investigated and their selective application leads to improved accuracy. The combined effect of the two proposed adaptation methods is also confirmed in transcription of real academic presentation.ja
dc.format.mimetypeapplication/pdfja
dc.language.isoengja
dc.publisherIEEEja
dc.rights© 2004 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.ja
dc.titleLanguage Model and Speaking Rate Adaptation for Spontaneous Presentation Speech Recognitionja
dc.type.niitypeJournal Articleja
dc.identifier.ncidAA10888994ja
dc.identifier.jtitleIEEE Transactions on Speech and Audio Processingja
dc.identifier.volume12ja
dc.identifier.issue4ja
dc.identifier.spage391ja
dc.identifier.epage400ja
dc.relation.doi10.1109/TSA.2004.828641ja
dc.textversionpublisherja
出現コレクション:学術雑誌掲載論文等

アイテムの簡略レコードを表示する

Export to RefWorks


出力フォーマット 


このリポジトリに保管されているアイテムはすべて著作権により保護されています。