Apparatus, method and computer program product for recognizing speech

  • US 7,974,844 B2
  • Filed: 03/01/2007
  • Issued: 07/05/2011
  • Est. Priority Date: 03/24/2006
  • Status: Active Grant
  • ×
    • Pin Icon | RPX Insight
    • Pin
First Claim
Patent Images

1. A speech recognition apparatus comprising:

  • a semantic-relation storage unit that stores semantic relation among words and relevance ratio indicating degree of the semantic relation in association with each other;

    a first input accepting unit that accepts an input of a first speech;

    a first candidate producing unit that recognizes the first speech and produces first recognition candidates and first likelihood of the first recognition candidates, the first recognition candidates containing a phoneme-string candidate and a word candidate;

    a first-candidate selecting unit that selects one of the first recognition candidates as a recognition result of the first speech based on the first likelihood of the first recognition candidates;

    a second input accepting unit that accepts an input of a second speech including an object word and a clue word, wherein the first speech includes the object word, the first speech does not include the clue word, and the recognition result of the first speech does not include the object word, and wherein the clue word provides the clue for recognizing the object word and for correcting a portion of the recognition result of the first speech which corresponds to the object word;

    a second candidate producing unit that recognizes the second speech and produces second recognition candidates and second likelihood of the second recognition candidates;

    a word extracting unit that extracts recognition candidates of the object word and recognition candidates of the clue word from the second recognition candidates;

    a second-candidate selecting unit that acquires the relevance ratio associated with the semantic relation between the extracted recognition candidates of the object word and the extracted recognition candidates of the clue word, from the semantic-relation storage unit, and selects one of the second recognition candidates as a recognition result of the second speech based on the acquired relevance ratio;

    a correction-portion identifying unit that compares a phoneme-string contained in the recognition result of the first speech with a phoneme-string contained in the recognition candidates of the object word extracted by the word extracting unit, and identifies a portion corresponding to the object word; and

    a correcting unit that corrects the identified portion corresponding to the object word with a portion that contains the object word and that is contained in the recognition result of the second speech.

View all claims
    ×
    ×

    Thank you for your feedback

    ×
    ×