发明申请
US20080052072A1 SPEAKER RECOGNITION METHOD BASED ON STRUCTURED SPEAKER MODELING AND A SCORING TECHNIQUE
有权
基于结构化扬声器建模和分频技术的扬声器识别方法
- 专利标题： SPEAKER RECOGNITION METHOD BASED ON STRUCTURED SPEAKER MODELING AND A SCORING TECHNIQUE
- 专利标题（中）： 基于结构化扬声器建模和分频技术的扬声器识别方法
-
申请号： US11930970申请日： 2007-10-31
-
公开(公告)号： US20080052072A1公开(公告)日： 2008-02-28
- 发明人: Upendra Chaudhari , Stephane Maes , Jiri Navratil
- 申请人： Upendra Chaudhari , Stephane Maes , Jiri Navratil
- 申请人地址： US NY Armonk
- 专利权人： International Business Corporation
- 当前专利权人： International Business Corporation
- 当前专利权人地址： US NY Armonk
- 主分类号： G10L15/00
- IPC分类号： G10L15/00
摘要：
A technique for improved score calculation and normalization in a framework of recognition with phonetically structured speaker models. The technique involves determining, for each frame and each level of phonetic detail of a target speaker model, a non-interpolated likelihood value, and then resolving the at least one likelihood value to obtain a likelihood score.
公开/授权文献
信息查询
