Art

J-GLOBAL ID：200902101812488778   Reference number：01A0184154

Large Vocabulary Continuous Speech Recognition Based on Phonetic Tied-Mixture Model.

Phonetic Tied-Mixtureモデルを用いた大語い連続音声認識

Author (4)： RI AKINOBU (京大) ,  KAWAHARA TATSUYA (京大) ,  TAKEDA KAZUYA (名古屋大) ,  SHIKANO KIYOHIRO (奈良先端科学技術大学院大)
Material： 電子情報通信学会論文誌 D-2  (IEICE Transactions on Information and Systems, Pt.2 (Japanese Edition))
Volume： J83-D-2  Issue： 12  Page： 2517-2525  Publication year： Dec. 25, 2000 
JST Material Number： L0197A  ISSN： 0915-1923  Document type： Article
Article type： 原著論文  Country of issue： Japan (JPN)  Language： JAPANESE (JA)

Thesaurus term： *continuous speech recognition ,...

   To see more with JDream III (charged).   {{ this.onShowAbsJLink("http://jdream3.com/lp/jglobal/index.html?docNo=01A0184154&from=J-GLOBAL&jstjournalNo=L0197A") }}

JST classification (1)： Pattern recognition  (JE07000S)

Reference (11)：

• YOUNG, S. J. The general use of tying in phonemedased HMM speech recognizer. Proc. IEEEICASSP. 1992, 569-572
• HUANG, X. D. On semi-continuous hidden Markov modeling. Proc. IEEEICASSP. 1990, 689-692
• LEE, C. H. Acoustic modeling for large vocabulary speech recognition. Compter Speech and Language. 1990, 4, 2, 127-166
• ZAVALIAGKOS, G. The BBN BYBLOS 1997 large vocabulary conversational speech recognition system. Proc. IEEE-ICASSP. 1998, 905-908
• DIGALAKIS, V. Genones: Optimizing the degree of mixture tying in a large vocabulary hidden Markov model based speech recognizer. Proc. IEEE-ICASSP. 1994, I-537-540

Terms in the title (2)： モデル ,  大語い連続音声認識