Resolution enhancement of speech signals for speech synthesis
US10510358B1 · kind B1 · utility
8Cited by
4References
17Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Sep 29, 2017 |
| Grant date | Dec 17, 2019 |
| Priority date | — |
| Expiry date | Nov 30, 2037 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L25/30
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
An approach to speech synthesis uses two phases in which a relatively low quality waveform is computed, and that waveform is passed through an enhancement phase which generates the waveform that is ultimately used to produce the acoustic signal provided to the user. For example, the first phase and the second phase are each implemented using a separate artificial neural network. The two phases may be computationally preferable to using a direct approach to yield a synthesized waveform of comparable quality.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.