×

Systems and methods of improving automated speech recognition accuracy using statistical analysis of search terms

  • US 8,543,393 B2
  • Filed: 05/20/2008
  • Issued: 09/24/2013
  • Est. Priority Date: 05/20/2008
  • Status: Active Grant
First Claim
Patent Images

1. A system of statistically analyzing search terms for detection by a speech recognition engine, comprisingan interface adapted to receive a text-based search term;

  • a textual-linguistic analysis module adapted to detect one or more textual features within the search term and generate a first numeric score associated with the search term, the first numeric score comprising an unbounded score representing the sum of all textual features contained within the search term;

    a phonetic conversion module adapted to convert the text-based search term into a phoneme string;

    a phonemic-linguistic analysis module adapted to detect one or more phonemic features within the phoneme string and generate a second numeric score associated with the search term, the second numeric score comprising an unbounded score representing the sum of all phonemic features contained within the phoneme string;

    a score normalization module adapted to normalize the first and second numeric scores and output a numeric search term score to a user or process, wherein the numeric search term score correlates with a probability that the search term will be accurately identified by a speech recognition engine.

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