System and method for updating an adaptive speech recognition model

  • US 9,697,822 B1
  • Filed: 04/28/2014
  • Issued: 07/04/2017
  • Est. Priority Date: 03/15/2013
  • Status: Active Grant
  • ×
    • Pin Icon | RPX Insight
    • Pin
First Claim
Patent Images

1. A machine-implemented method, comprising:

  • determining that a first user of a first mobile communication device is engaged in a call over a communications network;

    providing an adaptive speech recognition model comprising a speaker-dependent speech recognition model;

    after providing the adaptive speech recognition model, analyzing an outbound audio channel of a baseband unit of the first mobile communication device to obtain a call audio signal corresponding to audio input from one or more microphones of the first mobile communication device; and

    updating the adaptive speech recognition model with training data derived from the call audio signal.

View all claims
  • 0 Assignments