Systems and methods for selecting from multiple phonectic transcriptions for text-to-speech synthesis
US7869999B2 · kind B2 · utility
306Cited by
20References
19Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Aug 10, 2005 |
| Grant date | Jan 11, 2011 |
| Priority date | — |
| Expiry date | Aug 29, 2027 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L13/08
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A system and method for generating synthetic speech, which operates in a computer implemented Text-To-Speech system. The system comprises at least a speaker database that has been previously created from user recordings, a Front-End system to receive an input text and a Text-To-Speech engine. The Front-End system generates multiple phonetic transcriptions for each word of the input text, and the TTS engine uses a cost function to select which phonetic transcription is the more appropriate for searching the speech segments within the speaker database to be concatenated and synthesized.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.