发明授权
US07516067B2 Method and apparatus using harmonic-model-based front end for robust speech recognition
有权
使用基于谐波模型的前端进行鲁棒语音识别的方法和装置
- 专利标题： Method and apparatus using harmonic-model-based front end for robust speech recognition
- 专利标题（中）： 使用基于谐波模型的前端进行鲁棒语音识别的方法和装置
-
申请号： US10647586申请日： 2003-08-25
-
公开(公告)号： US07516067B2公开(公告)日： 2009-04-07
- 发明人: Michael Seltzer , James Droppo , Alejandro Acero
- 申请人： Michael Seltzer , James Droppo , Alejandro Acero
- 申请人地址： US WA Redmond
- 专利权人： Microsoft Corporation
- 当前专利权人： Microsoft Corporation
- 当前专利权人地址： US WA Redmond
- 代理机构： Westman, Champlin & Kelly, P.A.
- 代理商 Theodore M. Magee
- 主分类号： G10L21/02
- IPC分类号： G10L21/02 ; G10L15/00 ; G10L15/20
摘要：
A system and method are provided that reduce noise in speech signals. The system and method decompose a noisy speech signal into a harmonic component and a residual component. The harmonic component and residual component are then combined as a sum to form a noise-reduced value. In some embodiments, the sum is a weighted sum where the harmonic component is multiplied by a scaling factor. In some embodiments, the noise-reduced value is used in speech recognition.
公开/授权文献
信息查询
