Patent · US Active

Learning front-end speech recognition parameters within neural network training

US10360901B2 · kind B2 · utility

4Cited by
1References
26Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 5, 2014
Grant dateJul 23, 2019
Priority date
Expiry dateApr 15, 2035

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L25/18
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Techniques for learning front-end speech recognition parameters as part of training a neural network classifier include obtaining an input speech signal, and applying front-end speech recognition parameters to extract features from the input speech signal. The extracted features may be fed through a neural network to obtain an output classification for the input speech signal, and an error measure may be computed for the output classification through comparison of the output classification with a known target classification. Back propagation may be applied to adjust one or more of the front-end parameters as one or more layers of the neural network, based on the error measure.

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