Method and device for performing voice recognition using grammar model

Abstract

A method of updating speech recognition data including a language model used for speech recognition, the method including obtaining language data including at least one word; detecting a word that does not exist in the language model from among the at least one word; obtaining at least one phoneme sequence regarding the detected word; obtaining components constituting the at least one phoneme sequence by dividing the at least one phoneme sequence into predetermined unit components; determining information regarding probabilities that the respective components constituting each of the at least one phoneme sequence appear during speech recognition; and updating the language model based on the determined probability information.

What is claimed: 
     
       1. A method of performing speech recognition of a voice spoken by a user, the method comprising:
 obtaining first audio data based on the voice spoken by the user detected by a first electronic device; 
 obtaining second audio data based on the voice spoken by the user detected by a second electronic device; 
 determining first audio quality of the first audio data; 
 determining second audio quality of the second audio data; 
 selecting audio data from among the first audio data and the second audio data, based on the first audio quality and the second audio quality; 
 selecting an electronic device that obtained the audio data from among the first electronic device and the second electronic device; 
 performing speech recognition of the voice spoken by the user, based on the audio data; and 
 outputting a result of the speech recognition at the electronic device. 
 
     
     
       2. The method of  claim 1 , wherein the first audio quality comprises a first volume of the first audio data, and
 wherein the second audio quality comprises a second volume of the second audio data. 
 
     
     
       3. The method of  claim 1 , wherein the first audio quality comprises a first signal to noise ratio of the first audio data, and
 wherein the second audio quality comprises a second signal to noise ratio of the second audio data. 
 
     
     
       4. The method of  claim 1 , wherein the first audio data comprises at least one of a first volume of the first audio data and a first signal to noise ratio of the first audio data, and
 wherein the second audio data comprises at least one of a second volume of the second audio data and a second signal to noise ratio of the second audio data. 
 
     
     
       5. An electronic device for performing speech recognition of a voice spoken by a user, the electronic device comprising:
 a memory storing computer-readable instructions; and 
 at least one processor when executing the computer-readable instructions configured to obtain first audio data based on the voice spoken by the user detected by the electronic device, obtain second audio data based on the voice spoken by the user detected by a second electronic device, determine first audio quality of the first audio data, determine second audio quality of the second audio data, select the first audio data from among the first audio data and the second audio data, based on the first audio quality and the second audio quality, select the electronic device that obtained the first audio data from among the electronic device and the second electronic device, perform speech recognition of the voice spoken by the user, based on the audio data, and output a result of the speech recognition at the electronic device. 
 
     
     
       6. The electronic device of  claim 5 , wherein the first audio quality comprises a first volume of the first audio data, and
 wherein the second audio quality comprises a second volume of the second audio data. 
 
     
     
       7. The electronic device of  claim 5 , wherein the first audio quality comprises a first signal to noise ratio of the first audio data, and
 wherein the second audio quality comprises a second signal to noise ratio of the second audio data. 
 
     
     
       8. The electronic device of  claim 5 , wherein the first audio data comprises at least one of a first volume of the first audio data and a first signal to noise ratio of the first audio data, and
 wherein the second audio data comprises at least one of a second volume of the second audio data and a second signal to noise ratio of the second audio data. 
 
     
     
       9. A method of performing speech recognition of a voice spoken by a user, the method comprising:
 obtaining first audio data based on the voice spoken by the user detected by a first electronic device; 
 obtaining second audio data based on the voice spoken by the user detected by a second electronic device; 
 determining first audio quality of the first audio data; 
 determining second audio quality of the second audio data; 
 selecting a closest electronic device that is closest to the user from among the first electronic device and the second electronic device, based on the first audio quality and the second audio quality; 
 performing speech recognition of the voice spoken by the user based on the closest electronic device; and 
 outputting a result of the speech recognition at the closest electronic device. 
 
     
     
       10. The method of  claim 9 , wherein the first audio quality comprises a first volume of the first audio data, and
 wherein the second audio quality comprises a second volume of the second audio data. 
 
     
     
       11. The method of  claim 9 , wherein the first audio quality comprises a first signal to noise ratio of the first audio data, and
 wherein the second audio quality comprises a second signal to noise ratio of the second audio data. 
 
     
     
       12. The method of  claim 9 , wherein the first audio data comprises at least one of a first volume of the first audio data and a first signal to noise ratio of the first audio data, and
 wherein the second audio data comprises at least one of a second volume of the second audio data and a second signal to noise ratio of the second audio data. 
 
     
     
       13. An electronic device for performing speech recognition of a voice spoken by a user, the electronic device comprising:
 a memory storing computer-readable instructions; and 
 at least one processor when executing the computer-readable instructions configured to obtain first audio data based on the voice spoken by the user detected the electronic device, obtain second audio data based on the voice spoken by the user detected by a second electronic device, determine first audio quality of the first audio data, determine second audio quality of the second audio data, select the electronic device as a closest electronic device that is closest to the user from among the electronic device and the second electronic device, based on the first audio quality and the second audio quality, perform speech recognition of the voice spoken by the user based on the closest electronic device, and output a result of the speech recognition at the electronic device that is the closest electronic device closest to the user. 
 
     
     
       14. The electronic device of  claim 13 , wherein the first audio quality comprises a first volume of the first audio data, and
 wherein the second audio quality comprises a second volume of the second audio data. 
 
     
     
       15. The electronic device of  claim 13 , wherein the first audio quality comprises a first signal to noise ratio of the first audio data, and
 wherein the second audio quality comprises a second signal to noise ratio of the second audio data. 
 
     
     
       16. The electronic device of  claim 13 , wherein the first audio data comprises at least one of a first volume of the first audio data and a first signal to noise ratio of the first audio data, and
 wherein the second audio data comprises at least one of a second volume of the second audio data and a second signal to noise ratio of the second audio data. 
 
     
     
       17. A method of performing speech recognition of a voice spoken by a user, the method comprising:
 obtaining first audio data based on the voice spoken by the user received by a first electronic device;   obtaining second audio data based on the voice spoken by the user received by a second electronic device;   determining first audio quality of the first audio data;   determining second audio quality of the second audio data;   identifying an electronic device from among the first electronic device and the second electronic device, based on the first audio quality and the second audio quality;   performing speech recognition of a voice received by the identified electronic device; and   outputting a result of the speech recognition at the identified electronic device.    
     
     
       18. The method of claim 17, wherein the identifying the electronic device from among the first electronic device and the second electronic device comprises:
 selecting audio data from among the first audio data and the second audio data, based on the first audio quality and the second audio quality; and   identifying the electronic device that obtained the selected audio data from among the first electronic device and the second electronic device.    
     
     
       19. The method of claim 17, wherein the first audio quality comprises a first volume of the first audio data, and
 wherein the second audio quality comprises a second volume of the second audio data.    
     
     
       20. The method of claim 17, wherein the first audio quality comprises a first signal to noise ratio of the first audio data, and
 wherein the second audio quality comprises a second signal to noise ratio of the second audio data.    
     
     
       21. The method of claim 17, wherein the first audio data comprises at least one of a first volume of the first audio data and a first signal to noise ratio of the first audio data, and
 wherein the second audio data comprises at least one of a second volume of the second audio data and a second signal to noise ratio of the second audio data.    
     
     
       22. An electronic device for performing speech recognition of a voice spoken by a user, the electronic device comprising:
 a memory storing computer-readable instructions; and   at least one processor when executing the computer-readable instructions configured to:
 obtain first audio data based on the voice spoken by the user received by the electronic device, 
 obtain second audio data based on the voice spoken by the user received by a second electronic device, 
 determine first audio quality of the first audio data, 
 determine second audio quality of the second audio data, 
 identify the electronic device from among the electronic device and the second electronic device, based on the first audio quality and the second audio quality, 
 perform speech recognition of a voice received by the identified electronic device, and 
 output a result of the speech recognition at the identified electronic device.  
   
     
     
       23. The electronic device of claim 22, The electronic device of claim 6, wherein the at least one processor is configured to:
 select audio data from among the first audio data and the second audio data, based on the first audio quality and the second audio quality; and   identify the electronic device that obtained the selected audio data from among the electronic device and the second electronic device.    
     
     
       24. The electronic device of claim 22, wherein the first audio quality comprises a first volume of the first audio data, and
 wherein the second audio quality comprises a second volume of the second audio data.    
     
     
       25. The electronic device of claim 22, wherein the first audio quality comprises a first signal to noise ratio of the first audio data, and
 wherein the second audio quality comprises a second signal to noise ratio of the second audio data.    
     
     
       26. The electronic device of claim 22, wherein the first audio data comprises at least one of a first volume of the first audio data and a first signal to noise ratio of the first audio data, and
 wherein the second audio data comprises at least one of a second volume of the second audio data and a second signal to noise ratio of the second audio data.    
     
     
       27. A method of performing speech recognition of a voice spoken by a user, the method comprising:
 obtaining first audio data based on the voice spoken by the user received by a first electronic device;   obtaining second audio data based on the voice spoken by the user received by a second electronic device;   determining first audio quality of the first audio data;   determining second audio quality of the second audio data;   identifying a closest electronic device that is closest to the user from among the first electronic device and the second electronic device, based on the first audio quality and the second audio quality;   performing speech recognition of a voice received by the closest electronic device; and   outputting a result of the speech recognition at the closest electronic device.    
     
     
       28. The method of claim 27, wherein the first audio quality comprises a first volume of the first audio data, and
 wherein the second audio quality comprises a second volume of the second audio data.    
     
     
       29. The method of claim 27, wherein the first audio quality comprises a first signal to noise ratio of the first audio data, and
 wherein the second audio quality comprises a second signal to noise ratio of the second audio data.    
     
     
       30. The method of claim 27, wherein the first audio data comprises at least one of a first volume of the first audio data and a first signal to noise ratio of the first audio data, and
 wherein the second audio data comprises at least one of a second volume of the second audio data and a second signal to noise ratio of the second audio data.    
     
     
       31. An electronic device for performing speech recognition of a voice spoken by a user, the electronic device comprising:
 a memory storing computer-readable instructions; and   at least one processor when executing the computer-readable instructions configured to   obtain first audio data based on the voice spoken by the user received by the electronic device,   obtain second audio data based on the voice spoken by the user received by a second electronic device,   determine first audio quality of the first audio data,   determine second audio quality of the second audio data,   identify the electronic device as a closest electronic device that is closest to the user from among the electronic device and the second electronic device, based on the first audio quality and the second audio quality,   perform speech recognition of a voice received by the closest electronic device, and   output a result of the speech recognition at the closest electronic device.    
     
     
       32. The electronic device of claim 31, wherein the first audio quality comprises a first volume of the first audio data, and
 wherein the second audio quality comprises a second volume of the second audio data.    
     
     
       33. The electronic device of claim 31, wherein the first audio quality comprises a first signal to noise ratio of the first audio data, and
 wherein the second audio quality comprises a second signal to noise ratio of the second audio data.    
     
     
       34. The electronic device of claim 31, wherein the first audio data comprises at least one of a first volume of the first audio data and a first signal to noise ratio of the first audio data, and
 wherein the second audio data comprises at least one of a second volume of the second audio data and a second signal to noise ratio of the second audio data.