发明名称 |
Method and system for generating natural sounding concatenative synthetic speech |
摘要 |
A method for generating synthetic speech can include identifying a recording of conversational speech and creating a transcription of the conversational speech. Using the transcription, rather than a predefined script, the recording can be analyzed and acoustic units extracted. Each acoustic unit can include a phoneme and/or a sub-phoneme. The acoustic units can be stored so that a concatenative text-to-speech engine can later splice the acoustic units together to produce synthetic speech.
|
申请公布号 |
US2004176957(A1) |
申请公布日期 |
2004.09.09 |
申请号 |
US20030378338 |
申请日期 |
2003.03.03 |
申请人 |
INTERNATIONAL BUSINESS MACHINES CORPORATION |
发明人 |
REICH DAVID E. |
分类号 |
G10L13/06;G10L13/08;G10L15/02;(IPC1-7):G10L13/08 |
主分类号 |
G10L13/06 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|