Patent · US Active

End-to-end speech diarization via iterative speaker embedding

US11887623B2 · kind B2 · utility

0Cited by
0References
26Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJun 22, 2021
Grant dateJan 30, 2024
Priority date
Expiry dateJul 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.