Methods and apparatuses for automatic speech recognition

  • US 10,283,110 B2
  • Filed: 07/07/2016
  • Issued: 05/07/2019
  • Est. Priority Date: 07/02/2009
  • Status: Active Grant
  • ×
    • Pin
First Claim
Patent Images

1. A method, comprising:

  • at an electronic device including at least a processor and a memory;

    receiving, by the processor, an input speech signal;

    generating first model parameters associated with a first representation of the input speech signal, the first representation being a discrete parameter representation;

    generating second model parameters associated with a second representation of the input speech signal, the second representation including a continuous parameter representation of residuals of the input speech signal;

    generating third model parameters to couple, in a vector space, the first representation with the second representation, wherein the first, second, and third model parameters are generated based on training at least one of a distortion model and a perception model;

    determining, using the vector space, one or more first model parameters that satisfy a predetermined threshold; and

    outputting, based on the one or more first model parameters that satisfy the predetermined threshold, a recognized sequence of words.

View all claims