End-to-end speech diarization via iterative speaker embedding
US11887623B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jun 22, 2021 |
| Grant date | Jan 30, 2024 |
| Priority date | — |
| Expiry date | Jul 1, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L19/008
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method includes receiving an input audio signal corresponding to utterances spoken by multiple speakers. The method also includes encoding the input audio signal into a sequence of T temporal embeddings. During each of a plurality of iterations each corresponding to a respective speaker of the multiple speakers, the method includes selecting a respective speaker embedding for the respective speaker by determining a probability that the corresponding temporal embedding includes a presence of voice activity by a single new speaker for which a speaker embedding was not previously selected during a previous iteration and selecting the respective speaker embedding for the respective speaker as the temporal embedding. The method also includes, at each time step, predicting a respective voice activity indicator for each respective speaker of the multiple speakers based on the respective speaker embeddings selected during the plurality of iterations and the temporal embedding.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.