Patent · US Active

Speech recognition with sequence-to-sequence models

US11335333B2 · kind B2 · utility

3Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 17, 2019
Grant dateMay 17, 2022
Priority date
Expiry dateNov 16, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L15/26
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method includes obtaining audio data for a long-form utterance and segmenting the audio data for the long-form utterance into a plurality of overlapping segments. The method also includes, for each overlapping segment of the plurality of overlapping segments: providing features indicative of acoustic characteristics of the long-form utterance represented by the corresponding overlapping segment as input to an encoder neural network; processing an output of the encoder neural network using an attender neural network to generate a context vector; and generating word elements using the context vector and a decoder neural network. The method also includes generating a transcription for the long-form utterance by merging the word elements from the plurality of overlapping segments and providing the transcription as an output of the automated speech recognition system.

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