Apparatus and methods for dynamically changing a language model based on recognized text

Abstract

The technology of the present application provides a method and apparatus to manage speech resources. The method includes using a text recognizer to detect a change in a speech application that requires the use of different resources. On detection of the change, the method loads the different resources without the user needing to exit the currently executing speech application.

We claim: 
     
         1 . A method performed on at least one processor for managing speech resources of a speech recognition engine, the method comprising the steps of:
 initiating a speech recognition engine with a first language model;   converting audio received by the speech recognition engine to interim text;   determine whether the interim text matches at least one trigger; and   if it is determined that the interim text does not match the at least one trigger, outputting the interim text as recognized text;   if it is determined that the interim text does match the at least one trigger, replacing the first language model with a second language model.   
     
     
         2 . The method of  claim 1  wherein the initiating step comprises initiating the speech recognition engine with a first user profile and the replacing step further comprises replacing the first user profile with a second user profile. 
     
     
         3 . The method of  claim 1  wherein, if it is determined that the interim text does match the at least one trigger, the method comprises the steps of:
 pausing the converting step until the first language model is replaced with the second language model and resuming the converting step. 
 
     
     
         4 . The method of  claim 3  wherein the step of converting the audio to interim text comprises correlating the audio and the text. 
     
     
         5 . The method of  claim 4  wherein correlating the audio and the text comprises creating a plurality of small audio files from the audio and converting the plurality of small audio files into a corresponding plurality of interim text files and wherein the outputted recognized text is concatenated from the plurality of interim text files. 
     
     
         6 . The method of  claim 4  wherein correlating the audio and the text comprises placing a plurality of markers in the audio and placing a corresponding plurality of tags in the text such that the markers and tags provide audio and text pairs. 
     
     
         7 . The method of  claim 4  wherein if it is determined that the interim text does match the at least one trigger, the method comprises the steps of:
 rewinding the audio based on the correlation between the correlation between the audio and the text; and 
 deleting the interim text corresponding to a rewound portion of the audio. 
 
     
     
         8 . The method of  claim 1  wherein the at least one trigger is linked to the second language model. 
     
     
         9 . The method of  claim 8  wherein the at least one trigger comprises a plurality of triggers and wherein the second language model comprises a plurality of language models. 
     
     
         10 . The method of  claim 1  wherein the at least one trigger is selected from a group of triggers consisting of: a word, a clause, a phrase, or a combination thereof. 
     
     
         11 . A speech recognition engine comprising:
 a speech recognizer, the speech recognizer to receive audio and convert the audio to interim text using at least a language model;   a text recognizer operationally coupled to the speech recognizer, the text recognizer to receive the interim text and recognize whether the interim text contains a trigger;   wherein when the text recognizer recognizes a trigger in the interim text, the speech recognizer replaces a current language model with a replacement language model, and   wherein when the text recognizer does not recognize the trigger in the interim text, the interim text is provided as recognized text.   
     
     
         12 . The speech recognition engine of  claim 11  further comprising a memory wherein the memory comprises a plurality of triggers and a plurality of language models wherein each of the plurality of triggers is linked to one of the plurality of language models. 
     
     
         13 . The speech recognition engine of  claim 12  wherein the interim text comprises a plurality of interim text files and the speech recognizer converts the audio into a plurality of audio files corresponding to a plurality of interim text files. 
     
     
         14 . The speech recognition engine of  claim 13  further comprising an index engine wherein the index engine correlates the plurality of audio files and the corresponding plurality of interim text files. 
     
     
         15 . The speech recognition engine of  claim 14  wherein the index engine rewinds the audio based on the correlation between the plurality of audio files and the plurality of interim text files when the text recognizer recognizes the trigger.