Art

J-GLOBAL ID：201002206878056280   Reference number：10A0295206

A Rapid Model Adaptation Technique for Emotional Speech Recognition with Style Estimation Based on Multiple-Regression HMM

重回帰HMMに基づくスタイル推定による感情音声認識のための高速モデル適応技術

Author (4)： IJIMA Yusuke (Tokyo Inst. Technol., Yokohama-shi, JPN) ,  NOSE Takashi (Tokyo Inst. Technol., Yokohama-shi, JPN) ,  TACHIBANA Makoto (Tokyo Inst. Technol., Yokohama-shi, JPN) ,  KOBAYASHI Takao (Tokyo Inst. Technol., Yokohama-shi, JPN)
Material： IEICE Transactions on Information and Systems (Institute of Electronics, Information and Communication Engineers)  (IEICE Trans Inf Syst (Inst Electron Inf Commun Eng))
Volume： E93-D  Issue： 1  Page： 107-115  Publication year： Jan. 01, 2010 
JST Material Number： L1371A  ISSN： 0916-8532  Document type： Article
Article type： 原著論文  Country of issue： Japan (JPN)  Language： ENGLISH (EN)

Thesaurus term： *speech recognition ,  Voice ,  information ,  human (sociology) ,  stochastic model ,  *hidden Markov model ,  approximation method ,  adaptive system ,  *emotional speech ,  mathematical model
Semi thesaurus term： hidden Markov model ,  model fitting ,  acoustic model ,  *emotional voice ,  linguistic information ,  *multiple regression ,  speaker

JST classification (2)： Pattern recognition  (JE07000S) ,  Speach processing  (JE05000E)

Reference (19)：

• COWIE, R. Emotion recognition in human-computer interaction. IEEE Signal Process. Mag. 2001, 18, 1, 32-80
• BOSCH, L. Emotions, speech and the ASR framework. Speech Commun. 2003, 40, 1-2, 213-225
• ATHANASELIS, T. ASR for emotional speech : Clarifying the issues and enhancing performance. Neural Netw. 2005, 18, 4, 437-444
• LEGGETTER, C. J. Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Comput. Speech Lang. 1995, 9, 2, 171-185
• EIDE, E. A parametric approach to vocal tract length normalization. Proc. ICASSP 96, May. 1996, 346-348

Terms in the title (6)： HMM ,  スタイル ,  推定 ,  感情 ,  音声認識 ,  モデル適応