Patent · US Active

Context-dependent state tying using a neural network

US9620145B2 · kind B2 · utility

34Cited by

6References

19Claims

0Family size

Assignee

Google LLC · US

Inventors

Michiel A. U. Bacchiani · Summit, US
David Rybach · Aachen, DE

Key dates

Filing date	May 20, 2014
Grant date	Apr 11, 2017
Priority date	—
Expiry date	Sep 5, 2034

Classification

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

Abstract

The technology described herein can be embodied in a method that includes receiving an audio signal encoding a portion of an utterance, and providing, to a first neural network, data corresponding to the audio signal. The method also includes generating, by a processor, data representing a transcription for the utterance based on an output of the first neural network. The first neural network is trained using features of multiple context-dependent states, the context-dependent states being derived from a plurality of context-independent states provided by a second neural network.

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