Art

J-GLOBAL ID：200902193630709355   Reference number：00A0283064

MDL-based context-dependent subword modeling for speech recognition.

音声認識のためのMDL基準に基づく環境依存認識単位のモデリング

Author (2)： SHINODA K (NEC Corp., Kawasaki, JPN) ,  WATANABE T (NEC Corp., Kawasaki, JPN)
Material： Journal of the Acoustical Society of Japan. E  (J Acoust Soc Jpn E)
Volume： 21  Issue： 2  Page： 79-86  Publication year： Mar. 2000 
JST Material Number： Z0931A  ISSN： 0388-2861  Document type： Article
Article type： 原著論文  Country of issue： Japan (JPN)  Language： ENGLISH (EN)

Thesaurus term： *speech recognition ,...

   To see more with JDream III (charged).   {{ this.onShowAbsJLink("http://jdream3.com/lp/jglobal/index.html?docNo=00A0283064&from=J-GLOBAL&jstjournalNo=Z0931A") }}

JST classification (1)： Pattern recognition  (JE07000S)

Reference (14)：

• 1) K.-F. Lee, S. Hayamizu, H.-W. Hon, C. Huang, J. Swartz, and R. Weide, “Allophone clustering for continuous speech recognition,” Proc. ICASSP90, Albuquerque, 749-753 (1990).
• 2) M.-Y. Hwang, X. Huang, and F. Alleva, “Predicting unseen triphones with senones,” Proc. ICASSP93, Minneapolis, II-311-314 (1993).
• 3) V. Digalakis, P. Monaco, and H. Murveit, “Genons: Generalized mixture tying in continuous hidden Markov model-based speech recognizers,” IEEE Trans. SAP 4, 281-289 (1996).
• 4) S.J. Young, “The general use of tying in phonemebased HMM speech recognizers,” Proc. ICASSP92, San Francisco, 569-572 (1992).
• 5) J. Takami and S. Sagayama, “A successive state splitting algorithm for efficient allophone modeling,” Proc. ICASSP92, San Francisco, I-573-576 (1992).

Terms in the title (4)： 音声認識 ,  MDL基準 ,  環境 ,  モデリング