Art

J-GLOBAL ID：200902194643752469   Reference number：99A0670134

Automatic Selection of Training Utterances to Improve an Acoustic Model.

音響モデル精度向上のための学習サンプル自動選択

Author (3)： SATO SHOEI (NHK 放送技研) ,  IMAI TOORU (NHK 放送技研) ,  ANDO AKIO (NHK 放送技研)
Material： 電子情報通信学会技術研究報告  (IEICE Technical Report (Institute of Electronics, Information and Communication Engineers))
Volume： 99  Issue： 121(SP99 26-39)  Page： 27-32  Publication year： Jun. 18, 1999 
JST Material Number： S0532B  ISSN： 0913-5685  Document type： Proceedings
Article type： 原著論文  Country of issue： Japan (JPN)  Language： JAPANESE (JA)

Thesaurus term： modeling ,...
Semi thesaurus term： acoustic model ,...

   To see more with JDream III (charged).   {{ this.onShowAbsJLink("http://jdream3.com/lp/jglobal/index.html?docNo=99A0670134&from=J-GLOBAL&jstjournalNo=S0532B") }}

JST classification (1)： Pattern recognition  (JE07000S)

Reference (7)：

• GISH, H. Segregation of Speakers for Speech Recognition and Speaker Identification. IEEE International Conference on Acoustics, Speech, & Signal Processing Conference Proceedings, 1991. 1991, 873-876
• BIMBOT, F. Text-Free Speaker Recognition using an Arithmetic Harmonic Sphericity Measure. Proc. Eurospeech, 1993. 1993, 1, 160-172
• JOHNSON, S. E. Speaker Clustering Using Direct Maximisation of the MLLR-Adapted Likelihood. ICSLP'98. 1998, 1775-1778
• KUREMATSU, A. Japanese speech database as a tool of speech recognition and synthesis. Speech Communication. 9, 357-363
• HAYAMIZU, S. Design and creation of speech and text corpora of dialogue. IEICE Trans. Inf. Syst., D(1). 1993, E76, 17-22

Terms in the title (3)： 音響モデル ,  精度向上 ,  学習サンプル