Speaker embeddings for improved automatic speech recognition
US12136410B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | May 3, 2022 |
| Grant date | Nov 5, 2024 |
| Priority date | — |
| Expiry date | Apr 14, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2021/0135
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method includes receiving a reference audio signal corresponding to reference speech spoken by a target speaker with atypical speech, and generating, by a speaker embedding network configured to receive the reference audio signal as input, a speaker embedding for the target speaker. The speaker embedding conveys speaker characteristics of the target speaker. The method also includes receiving a speech conversion request that includes input audio data corresponding to an utterance spoken by the target speaker associated with the atypical speech. The method also includes biasing, using the speaker embedding generated for the target speaker by the speaker embedding network, a speech conversion model to convert the input audio data corresponding to the utterance spoken by the target speaker associated with atypical speech into an output canonical representation of the utterance spoken by the target speaker.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.