Disturbance component suppressing device, computer program, and speech recognition system

作者: 雅清 藤本 , Masakiyo Fujimoto , Satoru Nakamura , 哲 中村

DOI:

关键词:

摘要: PROBLEM TO BE SOLVED: To provide a disturbance component suppressing device which improves speech recognizing performance in actual environment wherein there is an influence of such as additive noise and reverberation present can suppress components short time. SOLUTION: A suppression section 114 includes probability distribution estimation portion 200 receives feature quantities 124 extracted frames designated time length divided by periods to observation signal obtained observing target multiplicative distortion are generated generates parameters 206 representing one after another using particle filter having plurality particles, parameter generation 202 screen 204 calculate estimated 126 the signal, disturbance, GMM 130. COPYRIGHT: (C)2006,JPO&NCIPI

参考文章(2)
Lalit R. Bahl, Speech recognition system The Journal of the Acoustical Society of America. ,vol. 85, pp. 2246- 2246 ,(1989) , 10.1121/1.397805