Invention Application
WO2008030756A2 METHOD AND SYSTEM FOR TRAINING A TEXT-TO-SPEECH SYNTHESIS SYSTEM USING A SPECIFIC DOMAIN SPEECH DATABASE
审中-公开
使用特定领域语音数据库训练文本到语音合成系统的方法和系统
- Patent Title: METHOD AND SYSTEM FOR TRAINING A TEXT-TO-SPEECH SYNTHESIS SYSTEM USING A SPECIFIC DOMAIN SPEECH DATABASE
- Patent Title (中): 使用特定领域语音数据库训练文本到语音合成系统的方法和系统
-
Application No.: PCT/US2007/077227Application Date: 2007-08-30
-
Publication No.: WO2008030756A2Publication Date: 2008-03-13
- Inventor: SCHROETER, Horst, Juergen
- Applicant: AT & T CORP. , SCHROETER, Horst, Juergen
- Applicant Address: 32 Avenue of the Americas New York, NY 10013-2412 US
- Assignee: AT & T CORP.,SCHROETER, Horst, Juergen
- Current Assignee: AT & T CORP.,SCHROETER, Horst, Juergen
- Current Assignee Address: 32 Avenue of the Americas New York, NY 10013-2412 US
- Agency: ISAACSON, Thomas, M.
- Priority: US11/530,258 20060908
Abstract:
A system, method and computer readable medium that trains a text-to-speech synthesis system for use in speech synthesis is disclosed. The method may include recording audio files of one or more live voices speaking language used in a specific domain, the audio files being recorded using various prosodies, storing the recorded audio files in a speech database; and training a text-to-speech synthesis system using the speech database, wherein the text-to-speech synthesis system selects audio selects audio segments having a prosody based on at least one dialog state and one speech act.
Information query
