Patent · US Active

System and methods for adapting neural network acoustic models

US10366687B2 · kind B2 · utility

9Cited by

2References

14Claims

0Family size

Assignee

Nuance Communications, Inc. · US

Inventors

Puming Zhan · Acton, US
Xinwei Li · Beijing, CN

Key dates

Filing date	Dec 10, 2015
Grant date	Jul 30, 2019
Priority date	—
Expiry date	Dec 10, 2035

Classification

Technology area (CPC G)Physics
CPC primaryG10L17/02
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Techniques for adapting a trained neural network acoustic model, comprising using at least one computer hardware processor to perform: generating initial speaker information values for a speaker; generating first speech content values from first speech data corresponding to a first utterance spoken by the speaker; processing the first speech content values and the initial speaker information values using the trained neural network acoustic model; recognizing, using automatic speech recognition, the first utterance based, at least in part on results of the processing; generating updated speaker information values using the first speech data and at least one of the initial speaker information values and/or information used to generate the initial speaker information values; and recognizing, based at least in part on the updated speaker information values, a second utterance spoken by the speaker.

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