Patent · US Active

Using context information with end-to-end models for speech recognition

US11545142B2 · kind B2 · utility

0Cited by

4References

28Claims

0Family size

Assignee

Google LLC · US

Inventors

Ding Zhao · Anjo, JP
Bo Li · 东风镇, CN
Ruoming Pang · New York, US
Tara N. Sainath · Jersey City, US
David Rybach · Aachen, DE
Deepti Bhatia · Fremont, US
Zelin Wu · Shanghai, CN

Key dates

Filing date	Mar 24, 2020
Grant date	Jan 3, 2023
Priority date	—
Expiry date	Jun 22, 2040

Classification

Technology area (CPC G)Physics
CPC primaryG10L2015/228
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A method includes receiving audio data encoding an utterance, processing, using a speech recognition model, the audio data to generate speech recognition scores for speech elements, and determining context scores for the speech elements based on context data indicating a context for the utterance. The method also includes executing, using the speech recognition scores and the context scores, a beam search decoding process to determine one or more candidate transcriptions for the utterance. The method also includes selecting a transcription for the utterance from the one or more candidate transcriptions.

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