发明授权
- 专利标题: Voice personalization of speech synthesizer
- 专利标题(中): 语音合成器的语音个性化
-
申请号: US09792928申请日: 2001-02-26
-
公开(公告)号: US06970820B2公开(公告)日: 2005-11-29
- 发明人: Jean-Claude Junqua , Florent Perronnin , Roland Kuhn , Patrick Nguyen
- 申请人: Jean-Claude Junqua , Florent Perronnin , Roland Kuhn , Patrick Nguyen
- 申请人地址: JP Osaka
- 专利权人: Matsushita Electric Industrial Co., Ltd.
- 当前专利权人: Matsushita Electric Industrial Co., Ltd.
- 当前专利权人地址: JP Osaka
- 代理机构: Harness, Dickey & Pierce, PLC
- 主分类号: G10L13/08
- IPC分类号: G10L13/08 ; G10L13/02 ; G10L13/04 ; G10L13/06 ; G10L21/00 ; G10L13/00
摘要:
The speech synthesizer is personalized to sound like or mimic the speech characteristics of an individual speaker. The individual speaker provides a quantity of enrollment data, which can be extracted from a short quantity of speech, and the system modifies the base synthesis parameters to more closely resemble those of the new speaker. More specifically, the synthesis parameters may be decomposed into speaker dependent parameters, such as context-independent parameters, and speaker independent parameters, such as context dependent parameters. The speaker dependent parameters are adapted using enrollment data from the new speaker. After adaptation, the speaker dependent parameters are combined with the speaker independent parameters to provide a set of personalized synthesis parameters. To adapt the parameters with a small amount of enrollment data, an eigenspace is constructed and used to constrain the position of the new speaker so that context independent parameters not provided by the new speaker may be estimated.
公开/授权文献
- US20020120450A1 Voice personalization of speech synthesizer 公开/授权日:2002-08-29