Speech recognition system interactive agent
First Claim
Patent Images
1. A method of performing speech recognition using an electronic interactive agent, comprising:
- forming a communications link between a client device and a server system adapted for streaming speech data;
providing a distributed speech recognition engine using resources from both the client device and the server system;
presenting the electronic interactive agent in a form perceptible to a user of the client device;
soliciting natural language speech utterance data in the form of continuous speech from the user of the device using the electronic interactive agent;
recognizing said speech utterance data using said distributed speech recognition engine to generate a recognized speech statement and processing said recognized speech statement using a natural language engine to identify a best response to said recognized speech statement among a number of predefined, stored queries and associated answers, the natural language engine being adapted to consider words not in said queries and associated answers to determine the best response;
if the best response is not identified with a specified confidence level using the natural language engine, presenting the recognized speech statement to one or more additional natural language engines;
controlling the electronic interactive agent to communicate the best 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.
1 Assignment
0 Petitions
Accused Products
Abstract
Methods and systems for performing speech recognition using an electronic interactive agent are disclosed. In embodiments of the invention, an electronic agent is presented in a form perceptible to a user. The electronic agent is used to solicit speech input from a user and to respond to the user'"'"'s recognized speech, and mimics the behavior of a human agent in a natural language query session with the user. The electronic agent may be implemented in a distributed speech recognition system in which speech recognition tasks are divided between client and server.
449 Citations
10 Claims
-
1. A method of performing speech recognition using an electronic interactive agent, comprising:
-
forming a communications link between a client device and a server system adapted for streaming speech data; providing a distributed speech recognition engine using resources from both the client device and the server system; presenting the electronic interactive agent in a form perceptible to a user of the client device; soliciting natural language speech utterance data in the form of continuous speech from the user of the device using the electronic interactive agent; recognizing said speech utterance data using said distributed speech recognition engine to generate a recognized speech statement and processing said recognized speech statement using a natural language engine to identify a best response to said recognized speech statement among a number of predefined, stored queries and associated answers, the natural language engine being adapted to consider words not in said queries and associated answers to determine the best response; if the best response is not identified with a specified confidence level using the natural language engine, presenting the recognized speech statement to one or more additional natural language engines; controlling the electronic interactive agent to communicate the best 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. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
Specification