Model generating method, and speech synthesis method and apparatus
US10832652B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Aug 14, 2017 |
| Grant date | Nov 10, 2020 |
| Priority date | — |
| Expiry date | Nov 27, 2037 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L13/08
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method is performed by at least one processor, and includes acquiring training speech data by concatenating speech segments having a lowest target cost among candidate concatenation solutions, and extracting training speech segments of a first annotation type, from the training speech data, the first annotation type being used for annotating that a speech continuity of a respective one of the training speech segments is superior to a preset condition. The method further includes calculating a mean dissimilarity matrix, based on neighboring candidate speech segments corresponding to the training speech segments before concatenation, the mean dissimilarity matrix representing a mean dissimilarity in acoustic features of groups of the neighboring candidate speech segments belonging to a same type of concatenation combination relationship, and generating a concatenation cost model having a target concatenation weight, based on the mean dissimilarity matrix, the concatenation cost model corresponding to the same type of concatenation combination relationship.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.