Patent · US Active

Automatic speech recognition

US11915690B1 · kind B1 · utility

10Cited by
0References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 29, 2021
Grant dateFeb 27, 2024
Priority date
Expiry dateNov 19, 2041

Classification

  • Technology area (CPC H)Electricity
  • CPC primaryH04R1/406
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A multi-channel transformer acoustic model that processes a plurality of audio signals output by microphones of a microphone array and outputs probabilities for acoustic units of an utterance represented in the audio signals. The audio signals represent the individual microphones' respective capturing of the utterance. The multi-channel model may perform self-attention on embeddings of the audio signals and then cross-channel attention across the attended audio signals. The cross-channel attention may involve processing of signals relative to each other to model the relationships across channels within and across time frames. The multi-channel model may include a transducer to perform processing frame-by-frame.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.