System and method for user-specified pronunciation of words for speech synthesis and recognition

  • US 9,620,104 B2
  • Filed: 06/06/2014
  • Issued: 04/11/2017
  • Est. Priority Date: 06/07/2013
  • Status: Active Grant
  • ×
    • Pin
First Claim
Patent Images

1. A method for learning word pronunciations, comprising:

  • at an electronic device with one or more processors and memory storing one or more programs for execution by the one or more processors;

    receiving a first speech input including at least one word;

    determining a first phonetic representation of the at least one word, the first phonetic representation comprising a first set of phonemes selected from a speech recognition phonetic alphabet;

    mapping the first set of phonemes to a second set of phonemes to generate a second phonetic representation, the second set of phonemes selected from a speech synthesis phonetic alphabet that is different from the speech recognition phonetic alphabet, wherein the speech recognition phonetic alphabet and the speech synthesis phonetic alphabet are phonetic alphabets of a same language; and

    storing the second phonetic representation in association with a text string corresponding to the at least one word.

View all claims