Patent · US Active

Method and system for building a topic specific language model for use in automatic speech recognition

US9697821B2 · kind B2 · utility

5Cited by
2References
8Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 16, 2013
Grant dateJul 4, 2017
Priority date
Expiry dateJul 22, 2035

Classification

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

Abstract

An automatic speech recognition method includes at a computer having one or more processors and memory for storing one or more programs to be executed by the processors, obtaining a plurality of speech corpus categories through classifying and calculating raw speech corpus; obtaining a plurality of classified language models that respectively correspond to the plurality of speech corpus categories through a language model training applied on each speech corpus category; obtaining an interpolation language model through implementing a weighted interpolation on each classified language model and merging the interpolated plurality of classified language models; constructing a decoding resource in accordance with an acoustic model and the interpolation language model; and decoding input speech using the decoding resource, and outputting a character string with a highest probability as a recognition result of the input speech.

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