Speech recognition system interactive agent

Abstract

A speech recognition system includes distributed processing across a client and server for recognizing a spoken query by a user. A number of different speech models for different languages are used to support and detect a language spoken by a user. In some implementations an interactive electronic agent responds in the user's language to facilitate a real-time, human like dialogue.

What is claimed is: 
     
         1 . A method of controlling an electronic interactive conversational agent comprising the steps of:
 a) forming a communications link between a client device and a server system;   b) presenting the electronic interactive conversational agent in a form perceptible to a user of the client device;   c) soliciting speech utterance data from the user of the device using the electronic interactive conversational agent;   d) performing one or more speech recognition operations on said speech utterance data to generate a recognized speech statement;   e) controlling the electronic interactive conversational agent to communicate a natural language voiced response to the recognized speech statement generated by the server system;
 wherein the electronic interactive conversational agent is adapted to mimic behavior of a human agent through a native language dialog session conducted with the user. 
   
     
     
         2 . The method of  claim 1 , wherein said communications link is an INTERNET connection established through a Web browser. 
     
     
         3 . The method of  claim 2  wherein the electronic interactive conversational agent is presented through said Web Browser. 
     
     
         4 . The method of  claim 1  wherein the electronic interactive conversational agent form is an animated character on a screen of the client device. 
     
     
         5 . The method of  claim 1 , further including a step: causing the electronic interactive conversational agent to communicate one or more suggestions for speech utterances to the user. 
     
     
         6 . The method of  claim 1  further including a step: configuring perception related parameters of the electronic interactive conversational agent, including one of a gender, a visual appearance, and/or voice characteristics including one of pitch, volume and/or speed. 
     
     
         7 . The method of  claim 6 , wherein said perception related parameters are set at least in part under control of the user of the client device. 
     
     
         8 . The method of  claim 6 , wherein said perception related parameters are set at least in part based on configuration data from the server system. 
     
     
         9 . The method of  claim 1 , wherein said perception related parameters are changed automatically and adapted based on an application being used by the user. 
     
     
         10 . The method of  claim 1 , wherein a speech recognition engine distributed between the client device and the server system generates said recognized speech statement. 
     
     
         11 . The method of  claim 1 , furthering including a step: performing a natural language operation to generate a meaning for said recognized speech statement. 
     
     
         12 . The method of  claim 1 , wherein the electronic interactive conversational agent is presented to the user in a search engine Web page. 
     
     
         13 . The method of  claim 1 , further including a step: providing additional multi-media information along with said natural language voiced response in response to a query presented by the user. 
     
     
         14 . A method of performing speech recognition using an electronic interactive agent comprising the steps of:
 a) forming a communications link between a client device and a server system adapted for streaming speech data;   b) providing a distributed speech recognition engine using resources from both the client device and the server system;   c) presenting the electronic interactive agent in a form perceptible to a user of the client device;   d) soliciting speech utterance data from the user of the device using the electronic interactive agent;   e) recognizing said speech utterance data using said distributed speech recognition engine to generate a recognized speech statement;   f) controlling the electronic interactive agent to communicate a response to the recognized speech statement generated by the server system;
 wherein the electronic interactive agent is adapted to mimic behavior of a human agent through a natural language query session conducted with the user. 
   
     
     
         15 . The method of  claim 14 , wherein the electronic interactive agent uses a native language voice during at least parts of the natural language query session. 
     
     
         16 . The method of  claim 14 , wherein the electronic interactive agent and distributed speech recognition engine are implemented as software routines 
     
     
         17 . The method of  claim 14 , wherein said communications link is an INTERNET connection established through a Web browser. 
     
     
         18 . The method of  claim 17  wherein the electronic interactive agent is presented through said Web Browser. 
     
     
         19 - 25 . (canceled) 
     
     
         26 . An electronic interactive conversational agent comprising:
 a) a first software routine for presenting the electronic interactive conversational agent in a form perceptible to a user of a client device;   b) a second software routine for soliciting speech utterance data from the user of the device using the electronic interactive conversational agent;   c) a speech recognition engine to perform one or more speech recognition operations on said speech utterance data to generate a recognized speech statement;
 wherein at least part of said speech recognition engine is implemented at a server system coupled to the client device through a communications link; 
   d) a third software routine to cause the electronic interactive conversational agent to communicate a natural language voiced response to the recognized speech statement generated by the server system;
 wherein the electronic interactive conversational agent is adapted to mimic behavior of a human agent through a native language dialog session conducted with the user. 
   
     
     
         27 . The system of  claim 26 , wherein the electronic interactive conversational agent is presented within a Web browser or a graphical interface. 
     
     
         28 . The system of  claim 26 , further including a routine for configuring perception related parameters of the electronic interactive conversational agent, including one of a gender, a visual appearance, and/or voice characteristics including one of pitch, volume and/or speed. 
     
     
         29 . The system of  claim 28 , wherein said perception related parameters are changed automatically and adapted based on an application being used by the user. 
     
     
         30 . The system of  claim 26 , further including a routine for providing additional multi-media information along with said natural language voiced response in response to a query presented by the user. 
     
     
         31 . A system for performing speech recognition using an electronic interactive agent comprising:
 a) a first routine for forming a communications link between a client device and a server system adapted for streaming speech data;   b) a distributed speech recognition engine which is implemented using resources from both the client device and the server system;   c) a second routine for presenting the electronic interactive agent in a form perceptible to a user of the client device;   d) a third routine for soliciting speech utterance data from the user of the device using the electronic interactive agent;
 wherein a recognized speech statement is generated by recognizing said speech utterance data using said distributed speech recognition engine; 
   e) a fourth routine for controlling the electronic interactive agent to communicate a response to the recognized speech statement generated by the server system;
 wherein the electronic interactive agent is adapted to mimic behavior of a human agent through a natural language query session conducted with the user. 
   
     
     
         32 . The system of  claim 31 , wherein the electronic interactive agent uses a native language voice during at least parts of the natural language query session. 
     
     
         33 . The system of  claim 31 , wherein the electronic interactive agent and distributed speech recognition engine are implemented as software routines. 
     
     
         34 - 40 . (canceled)