发明名称 PROCESSING UNIT, SPEECH RECOGNITION APPARATUS, SPEECH RECOGNITION SYSTEM, SPEECH RECOGNITION METHOD, AND SPEECH RECOGNITION PROGRAM
摘要 <P>PROBLEM TO BE SOLVED: To provide a processing unit, a speech recognition apparatus, a speech recognition system, a speech recognition method and a speech recognition program, capable of improving a speech recognition rate. <P>SOLUTION: The speech recognition apparatus which executes speech recognition on speech signals detected by a microphone provided in the environment comprises an initial reflection component extraction processing portion 11 which extracts initial reflection components by removing diffuse reverberation components from a reverberation pattern of an impulse response generated in the environment; and an acoustic model learning processing portion 14 which reflects the initial reflection components to speech data for learning to learn an acoustic model used for the speech recognition. <P>COPYRIGHT: (C)2010,JPO&INPIT
申请公布号 JP2009271359(A) 申请公布日期 2009.11.19
申请号 JP20080122288 申请日期 2008.05.08
申请人 TOYOTA MOTOR CORP;NARA INSTITUTE OF SCIENCE & TECHNOLOGY 发明人 WATABE SEISHO;KANO KIYOHIRO;GOMEZ RANDY
分类号 G10L15/06;G10L15/20 主分类号 G10L15/06
代理机构 代理人
主权项
地址