发明名称 |
ONLINE MAXIMUM-LIKELIHOOD MEAN AND VARIANCE NORMALIZATION FOR SPEECH RECOGNITION |
摘要 |
<p>A feature transform for speech recognition is described. An input speech utterance is processed to produce a sequence of representative speech vectors. A time-synchronous speech recognition pass is performed using a decoding search to determine a recognition output corresponding to the speech input. The decoding search includes, for each speech vector after some first threshold number of speech vectors, estimating a feature transform based on the preceding speech vectors in the utterance and partial decoding results of the decoding search. The current speech vector is then adjusted based on the current feature transform, and the adjusted speech vector is used in a current frame of the decoding search.</p> |
申请公布号 |
EP2539888(A1) |
申请公布日期 |
2013.01.02 |
申请号 |
EP20100708447 |
申请日期 |
2010.02.22 |
申请人 |
NUANCE COMMUNICATIONS, INC. |
发明人 |
WILLETT, DANIEL |
分类号 |
G10L15/08;G10L15/02;G10L15/07 |
主分类号 |
G10L15/08 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|