发明申请
US20050228664A1 Refining of segmental boundaries in speech waveforms using contextual-dependent models
失效
使用上下文相关模型对语音波形中的分段边界进行精细化
- 专利标题: Refining of segmental boundaries in speech waveforms using contextual-dependent models
- 专利标题(中): 使用上下文相关模型对语音波形中的分段边界进行精细化
-
申请号: US10823129申请日: 2004-04-13
-
公开(公告)号: US20050228664A1公开(公告)日: 2005-10-13
- 发明人: Yong Zhao , Min Chu , Jian-lai Zhou , Lijuan Wang
- 申请人: Yong Zhao , Min Chu , Jian-lai Zhou , Lijuan Wang
- 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
- 主分类号: G10L15/02
- IPC分类号: G10L15/02 ; G10L15/06
摘要:
A method and apparatus are provided for refining segmental boundaries in speech waveforms. Contextual acoustic feature similarities are used as a basis for clustering adjacent phoneme speech units, where each adjacent pair phoneme speech units include a segmental boundary. A refining model is trained for each cluster and used to refine boundaries of contextual phoneme speech units forming the clusters.