Text-to-speech (TTS) processing
US10692484B1 · kind B1 · utility
7Cited by
0References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jun 13, 2018 |
| Grant date | Jun 23, 2020 |
| Priority date | — |
| Expiry date | Dec 22, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L25/69
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A speech model is trained using multi-task learning. A first task may correspond to how well predicted audio matches training audio; a second task may correspond to a metric of perceived audio quality. The speech model may include, during training, layers related to the second task that are discarded at runtime.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.