发明授权
US4819271A Constructing Markov model word baseforms from multiple utterances by
concatenating model sequences for word segments
失效
通过连接字段的模型序列,从多个语句构建马尔科夫模型词基础
- 专利标题: Constructing Markov model word baseforms from multiple utterances by concatenating model sequences for word segments
- 专利标题(中): 通过连接字段的模型序列,从多个语句构建马尔科夫模型词基础
-
申请号: US133719申请日: 1987-12-16
-
公开(公告)号: US4819271A公开(公告)日: 1989-04-04
- 发明人: Lalit R. Bahl , Peter V. DeSouza , Robert L. Mercer , Michael A. Picheny
- 申请人: Lalit R. Bahl , Peter V. DeSouza , Robert L. Mercer , Michael A. Picheny
- 申请人地址: NY Armonk
- 专利权人: International Business Machines Corporation
- 当前专利权人: International Business Machines Corporation
- 当前专利权人地址: NY Armonk
- 主分类号: G10L11/00
- IPC分类号: G10L11/00 ; G10L15/06 ; G10L15/14 ; G10L5/00
摘要:
The present invention relates to apparatus and method for segmenting multiple utterances of a vocabulary word in a consistent and coherent manner and determining a Markov model sequence for each segment. A fenemic Markov model corresponds to each label.
公开/授权文献
- US5895198A Coil unloading rig 公开/授权日:1999-04-20