发明名称 |
Method and apparatus for predicting word prominence in speech synthesis |
摘要 |
A method and apparatus is provided for generating speech that sounds more natural. In one embodiment, word prominence and latent semantic analysis are used to generate more natural sounding speech. A method for generating speech that sounds more natural may comprise generating synthesized speech having certain word prominence characteristics and applying a semantically-driven word prominence assignment model to specify word prominence consistent with the way humans assign word prominence.
|
申请公布号 |
US2008091430(A1) |
申请公布日期 |
2008.04.17 |
申请号 |
US20070999323 |
申请日期 |
2007.12.04 |
申请人 |
BELLEGARDA JEROME R;SILVERMAN KIM E |
发明人 |
BELLEGARDA JEROME R.;SILVERMAN KIM E. |
分类号 |
G10L13/00 |
主分类号 |
G10L13/00 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|