发明名称 |
N-Best list rescoring in speech recognition |
摘要 |
A method of speech recognition processing is described based on an N-best list of recognition hypotheses corresponding to a spoken input. Each hypothesis on the N-best list is rescored based on its rank in the rescored N-best list. The rescoring may be based on a Statistical Language Model (SLM) or Dynamic Semantic Model (DSM). One or more rescoring categories may be associated with each recognition hypotheses to affect or bias the rescoring.
|
申请公布号 |
US2006190258(A1) |
申请公布日期 |
2006.08.24 |
申请号 |
US20050305825 |
申请日期 |
2005.12.16 |
申请人 |
VERHASSELT JAN;DERCKS HELMUT |
发明人 |
VERHASSELT JAN;DERCKS HELMUT |
分类号 |
G10L15/28 |
主分类号 |
G10L15/28 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|