Using non-parallel voice conversion for speech conversion models
US12190862B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 25, 2022 |
| Grant date | Jan 7, 2025 |
| Priority date | — |
| Expiry date | Mar 9, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2019/0001
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method includes receiving a set of training utterances each including a non-synthetic speech representation of a corresponding utterance, and for each training utterance, generating a corresponding synthetic speech representation by using a voice conversion model. The non-synthetic speech representation and the synthetic speech representation form a corresponding training utterance pair. At each of a plurality of output steps for each training utterance pair, the method also includes generating, for output by a speech recognition model, a first probability distribution over possible non-synthetic speech recognition hypotheses for the non-synthetic speech representation and a second probability distribution over possible synthetic speech recognition hypotheses for the synthetic speech representation. The method also includes determining a consistent loss term for the corresponding training utterance pair based on the first and second probability distributions and updating parameters of the speech recognition model based on the consistent loss term.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.