System and method of providing generated speech via a network

Abstract

A system and method of operating an automatic speech recognition application over an Internet Protocol network is disclosed. The ASR application communicates over a packet network such as an Internet Protocol network or a wireless network. A grammar for recognizing received speech from a user over the IP network is selected from a plurality of grammars according to a user-selected application. A server receives information representing speech over the IP network, performs speech recognition using the selected grammar, and returns information based upon the recognized speech. Sub-grammars may be included within the grammar to recognize speech from sub-portions of a dialog with the user.

We claim: 
     
         1 . A method comprising:
 transmitting over a network an identification of a spoken dialog application, the spoken dialog application having an associated grammar;   transmitting user speech over the network; and   receiving synthesized speech in response to the user speech, wherein the user speech was recognized by the spoken dialog application using the associated grammar.   
     
     
         2 . The method of  claim 1 , wherein recognizing the user speech using the associated grammar further comprises recognizing the user speech using a sub-grammar based on a sub-component of the user speech. 
     
     
         3 . The method of  claim 2 , wherein the sub-grammar is associated with a task. 
     
     
         4 . The method of  claim 1 , wherein the network is an internet protocol network. 
     
     
         5 . The method of  claim 1 , wherein the spoken dialog application carries on a dialog with a user communicating with a client. 
     
     
         6 . The method of  claim 1 , further comprising:
 receiving information based on the synthesized speech over an internet protocol network from a client.   
     
     
         7 . The method of  claim 1 , further comprising:
 modifying the associated grammar based at least in part on the user speech.   
     
     
         8 . A system comprising:
 a processor; and   a computer-readable storage medium storing instructions which, when executed on the processor, cause the processor to perform a method comprising:
 transmitting over a network an identification of a spoken dialog application, the spoken dialog application having an associated grammar; 
 transmitting user speech over the network; and 
 receiving synthesized speech in response to the user speech, wherein the user speech was recognized by the spoken dialog application using the associated grammar. 
   
     
     
         9 . The system of  claim 8 , wherein recognizing the user speech using the associated grammar further comprises recognizing the user speech using a sub-grammar based on a sub-component of the user speech. 
     
     
         10 . The system of  claim 9 , wherein the sub-grammar is associated with a task. 
     
     
         11 . The system of  claim 8 , wherein the network is an internet protocol network. 
     
     
         12 . The system of  claim 8 , wherein the spoken dialog application carries on a dialog with a user communicating with a client. 
     
     
         13 . The system of  claim 8 , the computer-readable storage medium storing additional instructions which, when executed on the processor cause the processor to perform a step comprising:
 receiving information based on the synthesized speech over an internet protocol network from a client.   
     
     
         14 . The system of  claim 8 , the computer-readable storage medium storing additional instructions which, when executed on the processor, cause the processor to perform a step comprising: modifying the associated grammar based at least in part on the user speech. 
     
     
         15 . A computer-readable storage medium storing instructions which, when executed by a processor, cause the processor, to perform steps comprising:
 transmitting over a network an identification of a spoken dialog application, the spoken dialog application having an associated grammar;   transmitting user speech over the network; and   receiving synthesized speech in response to the user speech, wherein the user speech was recognized by the spoken dialog application using the associated grammar.   
     
     
         16 . The computer-readable storage medium of  claim 15 , wherein recognizing the user speech using the associated grammar further comprises recognizing the user speech by using a sub-grammar based on a sub-component of the user speech. 
     
     
         17 . The computer-readable storage medium of  claim 16 , wherein the sub-grammar is associated with a task. 
     
     
         18 . The computer-readable storage medium of  claim 15 , wherein the network is an internet protocol network. 
     
     
         19 . The computer-readable storage medium of  claim 15 , wherein the spoken dialog application carries on a dialog with a user communicating with a client. 
     
     
         20 . The computer-readable storage medium of  claim 15  storing additional instructions which, when executed on the processor, cause the processor to perform a step comprising:
 receiving information based on the synthesized speech over an internet protocol network from a client.