发明授权
- 专利标题： Systems and methods for speech recognition
- 专利标题（中）： 用于语音识别的系统和方法
-
申请号： US14291138申请日： 2014-05-30
-
公开(公告)号： US09558741B2公开(公告)日： 2017-01-31
- 发明人: Lou Li , Li Lu , Xiang Zhang , Feng Rao , Shuai Yue , Bo Chen , Jianxiong Ma , Haibo Liu
- 申请人： Tencent Technology (Shenzhen) Company Limited
- 申请人地址： CN Shenzhen
- 专利权人： Tencent Technology (Shenzhen) Company Limited
- 当前专利权人： Tencent Technology (Shenzhen) Company Limited
- 当前专利权人地址： CN Shenzhen
- 代理机构： Jones Day
- 优先权： CN201310177246 20130514
- 主分类号： G10L15/28
- IPC分类号： G10L15/28 ; G10L15/08 ; G10L15/18 ; G10L15/183
摘要：
Systems and methods are provided for speech recognition. For example, audio characteristics are extracted from acquired voice signals; a syllable confusion network is identified based on at least information associated with the audio characteristics; a word lattice is generated based on at least information associated with the syllable confusion network and a predetermined phonetic dictionary; and an optimal character sequence is calculated in the word lattice as a speech recognition result.
公开/授权文献
- US20140350934A1 Systems and Methods for Voice Identification 公开/授权日：2014-11-27
信息查询
