Method and system for training a text-to-speech synthesis system using a domain-specific speech database
US7584104B2 · kind B2 · utility
7Cited by
2References
20Claims
0Family size
Assignee
Inventor
Key dates
| Filing date | Sep 8, 2006 |
| Grant date | Sep 1, 2009 |
| Priority date | — |
| Expiry date | Nov 20, 2027 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/22
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
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.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.