发明申请
US20120232902A1 SYSTEM AND METHOD FOR SPEECH RECOGNITION MODELING FOR MOBILE VOICE SEARCH
有权
用于移动语音搜索的语音识别建模的系统和方法
- 专利标题: SYSTEM AND METHOD FOR SPEECH RECOGNITION MODELING FOR MOBILE VOICE SEARCH
- 专利标题(中): 用于移动语音搜索的语音识别建模的系统和方法
-
申请号: US13042671申请日: 2011-03-08
-
公开(公告)号: US20120232902A1公开(公告)日: 2012-09-13
- 发明人: Enrico BOCCHIERI , Diamantino Antonio Caseiro , Dimitrios Dimitriadis
- 申请人: Enrico BOCCHIERI , Diamantino Antonio Caseiro , Dimitrios Dimitriadis
- 申请人地址: US GA Atlanta
- 专利权人: AT&T Intellectual Property I, L.P.
- 当前专利权人: AT&T Intellectual Property I, L.P.
- 当前专利权人地址: US GA Atlanta
- 主分类号: G10L15/06
- IPC分类号: G10L15/06
摘要:
Disclosed herein are systems, methods, and non-transitory computer-readable storage media for generating an acoustic model for use in speech recognition. A system configured to practice the method first receives training data and identifies non-contextual lexical-level features in the training data. Then the system infers sentence-level features from the training data and generates a set of decision trees by node-splitting based on the non-contextual lexical-level features and the sentence-level features. The system decorrelates training vectors, based on the training data, for each decision tree in the set of decision trees to approximate full-covariance Gaussian models, and then can train an acoustic model for use in speech recognition based on the training data, the set of decision trees, and the training vectors.
公开/授权文献
信息查询