Systems and methods of improving automated speech recognition accuracy using statistical analysis of search terms
First Claim
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.
6 Assignments
0 Petitions
Accused Products
Abstract
Systems and methods of improving speech recognition accuracy using statistical analysis of word or phrase-based search terms are disclosed. An illustrative system for statistically analyzing search terms includes an interface adapted to receive a text-based search term, a textual-linguistic analysis module that detects textual features within the search term and generates a first score, a phonetic conversion module that converts the search term into a phoneme string, a phonetic-linguistic analysis module that detects phonemic features within the phoneme string and generates a second score, and a score normalization module that normalizes the first and second scores and outputs a search term score to a user or process.
-
Citations
18 Claims
-
1. A system of statistically analyzing search terms for detection by a speech recognition engine, comprising
an 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 Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. A method of statistically analyzing search terms for detection by a speech recognition engine, comprising:
-
receiving a text-based search term from a user or process; analyzing one or more textual features within the search term using a textual-linguistic analysis module; computing a first numeric score associated with the one or more textual features within the search term, the first numeric score comprising an unbounded score representing the sum of all textual features contained within the search term; converting the search term into a phoneme string and analyzing one or more phonemic features within the phoneme string using a phonemic-linguistic analysis module; computing a second numeric score associated with the one or more phonemic features within the phoneme string, the second numeric score comprising an unbounded score representing the sum of all phonemic features contained within the phoneme string; and normalizing the first and second numeric scores and outputting a numeric search term score to the 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 Dependent Claims (11, 12, 13, 14, 15, 16, 17)
-
-
18. A method of statistically analyzing search terms for detection by a speech recognition engine, comprising:
-
providing a text-based search term to a search-term analysis module including a textual-linguistic analysis module and a phonemic-linguistic analysis module; performing a textual-linguistic analysis of the search term and generating a first numeric score based on one or more textual features found in the search term, the first numeric score representing the sum of all textual features contained within the search term; converting the search term into a phoneme string; performing a phonemic-linguistic analysis of the search term and generating a second numeric score based on one or more phonemic features found in the phoneme string, the second numeric score comprising an unbounded score representing the sum of all phonemic features contained within the phoneme string; normalizing the first and second numeric scores and outputting a search term score correlating with a probability that the search term will be accurately identified by a speech recognition engine; comparing the search term score against a threshold search term score, the threshold search term score corresponding to a threshold probability of identifying speech within a search term; and outputting the search term to a database if the search term score is at or above the threshold search term score.
-
Specification