×

Predicting pronunciation in speech recognition

  • US 10,339,920 B2
  • Filed: 03/04/2014
  • Issued: 07/02/2019
  • Est. Priority Date: 03/04/2014
  • Status: Active Grant
First Claim
Patent Images

1. A computer-implemented method for processing a spoken utterance, the method comprising:

  • receiving a single word comprising a first portion and a second portion;

    determining a first language of origin of the first portion;

    determining a first score associated with the first language of origin;

    determining a second language of origin of the second portion;

    determining a second score associated with the second language of origin;

    determining a plurality of potential pronunciations of the single word based at least in part on the first score and the second score, wherein each of the plurality of potential pronunciations is associated with a respective pronunciation score and wherein the plurality includes at least one hybrid pronunciation of the single word based on the first language of origin and the second language of origin;

    receiving a spoken utterance comprising a request to output audio content;

    matching a portion of the spoken utterance with one of the plurality of potential pronunciations based at least in part on a pronunciation score of one of the plurality of potential pronunciations;

    identifying the audio content based at least in part on the one of the plurality of potential pronunciations; and

    causing the audio content to be played by a computing device.

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