发明名称 |
METHOD OF CREATING AN ACOUSTIC MODEL FOR A SPEECH RECOGNITION SYSTEM |
摘要 |
<p>To create an acoustic model (U) for a speaker (3) as the user of a voice recognition system (6), a predetermined number of different group models that are typical of speaker groups (27, 28) are generated as initial models (Gi) and a weighted linear combination of the initial models (Gi) is created using previously determined weight factors (gi) that are specific to the acoustic model (U).</p> |
申请公布号 |
WO2004055780(A1) |
申请公布日期 |
2004.07.01 |
申请号 |
WO2003IB05775 |
申请日期 |
2003.12.02 |
申请人 |
KONINKLIJKE PHILIPS ELECTRONICS N.V.;BARTOSIK, HEINRICH |
发明人 |
BARTOSIK, HEINRICH |
分类号 |
G10L15/07;G10L15/187;(IPC1-7):G10L15/06 |
主分类号 |
G10L15/07 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|