×

MULTI-LEVEL SPEECH RECOGNITION

  • US 20150025890A1
  • Filed: 07/16/2014
  • Published: 01/22/2015
  • Est. Priority Date: 07/17/2013
  • Status: Active Grant
First Claim
Patent Images

1. A method of recognizing an utterance, comprising:

  • transmitting context data associated with a first device to a second device;

    receiving from the second device a first speech recognition model, wherein the first speech recognition model is a subset of a second speech recognition model present at the second device, and wherein the first speech recognition model is based on the context data;

    determining whether the utterance can be recognized at the first device based on the first speech recognition model;

    if the utterance cannot be recognized at the first device, sending at least a portion of the utterance to the second device; and

    if the utterance can be recognized at the first device, performing an action associated with the recognized utterance.

View all claims
  • 1 Assignment
Timeline View
Assignment View
    ×
    ×