System and method for augmenting spoken language understanding by correcting common errors in linguistic performance

Abstract

A method and system for automatic speech recognition are disclosed. The method comprises receiving speech from a user, the speech including at least one speech error, increasing the probabilities of closely related words to the at least one speech error and processing the received speech using the increased probabilities. A corpora of data having common words that are mis-stated is used to identify and increase the probabilities of related words. The method applies to at least the automatic speech recognition module and the spoken language understanding module.

1 . A method of processing speech, the method comprising:
 receiving speech from a user, the speech including at least one speech error;   modifying probabilities of closely related words to the at least one speech error based on a plurality of corpora of data having modified probabilities of certain words; and   processing via speech recognition the received speech using the modified probabilities.   
   
   
       2 . The method of  claim 1 , wherein processing the received speech further comprises automatic speech recognition of the received speech using the modified probabilities. 
   
   
       3 . The method of  claim 1 , wherein processing the received speech further comprises spoken language understanding of the received speech using the modified probabilities. 
   
   
       4 . The method of  claim 1 , wherein the closely related words are words that begin and end with similar sounds to the at least one speech error. 
   
   
       5 . The method of  claim 1 , wherein the closely related words are words that begin and end with the same phoneme and that have the same number of syllables as the at least one speech error. 
   
   
       6 . The method of  claim 1 , wherein the speech error comprises a plurality of words, and the closely related words sound similar to the plurality of words. 
   
   
       7 . The method of  claim 1 , further comprising using a corpora of data associated with the user's language patterns. 
   
   
       8 . The method of  claim 7 , wherein the user's language patterns relate to the language spoken by the user. 
   
   
       9 . The method of  claim 8 , wherein the corpora of data further comprises common speech errors made by speakers of the language spoken by the user. 
   
   
       10 . An language processing module in a spoken dialog system, the module comprising:
 means for receiving speech from a user, the speech including at least one speech error;   means for modifying the probabilities of closely related words to the at least one speech error based on a plurality of corpora of data having modified probabilities of certain words; and   means for processing via speech recognition the received speech using the modified probabilities.   
   
   
       11 . The module of  claim 10 , wherein the closely related words are words that begin and end with similar sounds to the at least one speech error. 
   
   
       12 . The module of  claim 10 , wherein the speech error comprises a plurality of words, and the closely related words sound similar to the plurality of words. 
   
   
       13 . The module of  claim 10 , further comprising using a corpora of data associated with the user's language patterns. 
   
   
       14 . The module of  claim 10 , wherein the closely related words are words that begin and end with the same phoneme and that have the same number of syllables as the at least one speech error. 
   
   
       15 . The module of  claim 13 , wherein the user's language patterns relate to the language spoken by the user. 
   
   
       16 . The module of  claim 15 , wherein the corpora of data further comprises common speech errors made by speakers of the language spoken by the user. 
   
   
       17 . A spoken dialog system having a speech processing module, the module comprising:
 means for receiving speech from a user, the speech including at least one speech error;   means for modifying probabilities of closely related words to the at least one speech error based on a plurality of corpora of data having modified probabilities of certain words; and   means for processing via speech recognition the received speech using the modified probabilities.   
   
   
       18 . The spoken dialog system of  claim 17 , wherein the module is an automatic speech recognition module. 
   
   
       19 . The spoken dialog system of  claim 17 , wherein the closely related words are words that begin and end with similar sounds to the at least one speech error. 
   
   
       20 . The spoken dialog system of  claim 17 , wherein the speech error comprises a plurality of words, and the closely related words sound similar to the plurality of words. 
   
   
       21 . The spoken dialog system of  claim 17 , further comprising using a corpora of data associated with the user's language patterns. 
   
   
       22 . The spoken dialog system of  claim 21 , wherein the user's language patterns relate to the language spoken by the user. 
   
   
       23 . The spoken dialog system of  claim 22 , wherein the corpora of data further comprises common speech errors made by speakers of the language spoken by the user. 
   
   
       24 . The spoken dialog system of  claim 17 , wherein the closely related words are words that begin and end with the same phoneme and that have the same number of syllables as the at least one speech error.