Patent · US Active

Generating acoustic models

US9786270B2 · kind B2 · utility

45Cited by

36References

20Claims

0Family size

Assignee

Google LLC · US

Inventors

Andrew W. Senior · New York, US
Hasim Sak · New York, US
Kanury Kanishka Rao · Santa Clara, US

Key dates

Filing date	Jul 8, 2016
Grant date	Oct 10, 2017
Priority date	—
Expiry date	Jul 8, 2036

Classification

Technology area (CPC G)Physics
CPC primaryG10L15/187
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating acoustic models. In some implementations, a first neural network trained as an acoustic model using the connectionist temporal classification algorithm is obtained. Output distributions from the first neural network are obtained for an utterance. A second neural network is trained as an acoustic model using the output distributions produced by the first neural network as output targets for the second neural network. An automated speech recognizer configured to use the trained second neural network is provided.

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