公开(公告)号：US20090164216A1

公开(公告)日：2009-06-25

申请号：US11963103

申请日：2007-12-21

申请人： Rathinavelu Chengalvarayan ,  Timothy J. Grost ,  Edward J. Abeska

发明人： Rathinavelu Chengalvarayan ,  Timothy J. Grost ,  Edward J. Abeska

IPC分类号： G10L15/00

CPC分类号： B60R16/0373

摘要： A method of circumstantial speech recognition in a vehicle. A plurality of parameters associated with a plurality of vehicle functions are monitored as an indication of current vehicle circumstances. At least one vehicle function is identified as a candidate for user-intended ASR control based on user interaction with the vehicle. The identified vehicle function is then used to disambiguate between potential commands contained in speech received from the user.

摘要翻译： 一种在车辆中进行语音识别的方法。 监视与多个车辆功能相关联的多个参数作为当前车辆环境的指示。 基于与车辆的用户交互，至少一个车辆功能被识别为用于用户意图的ASR控制的候选。 所识别的车辆功能然后用于消除从用户接收的语音中包含的潜在命令之间的歧义。