Method and system for statistic-based distance definition in text-to-speech conversion
US7590540B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Sep 29, 2005 |
| Grant date | Sep 15, 2009 |
| Priority date | — |
| Expiry date | Sep 20, 2027 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L13/04
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method for distance definition in a text-to-speech conversion system by applying Gaussian Mixture Model (GMM) to a distance definition. According to an embodiment, the text that is to be subjected to text-to-speech conversion is analyzed to obtain a text with descriptive prosody annotation; clustering is performed for samples in the obtained text; and a GMM model is generated for each cluster, to determine the distance between the sample and the corresponding GMM model.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.