×

Speech and Noise Models for Speech Recognition

  • US 20120022860A1
  • Filed: 09/30/2011
  • Published: 01/26/2012
  • Est. Priority Date: 06/14/2010
  • Status: Active Grant
First Claim
Patent Images

1. A system comprising:

  • one or more procession devices; and

    one or more storage devices storing instructions that, when executed by the one or more processing devices, cause the one or more processing devices to;

    receive an audio signal generated by a device based on audio input from a user, the audio signal including at least a user audio portion that corresponds to one or more user utterances recorded by the device;

    access a user speech model associated with the user;

    determine that background audio in the audio signal is below a defined threshold;

    in response to determining that the background audio in the audio signal is below the defined threshold, adapt the accessed user speech model based on the audio signal to generate an adapted user speech model that models speech characteristics of the user; and

    perform noise compensation on the received audio signal using the adapted user speech model to generate a filtered audio signal with reduced background audio compared to the received audio signal.

View all claims
  • 2 Assignments
Timeline View
Assignment View
    ×
    ×