Distributed internet based speech recognition system with natural language support
DCFirst Claim
1. A system for enabling a browser program to interact with a website using speech utterances, the system comprising:
- a speech recognition engine configured to generate a recognized speech query from an utterance;
said speech recognition engine being further configurable such that speech processing operations can be distributed between a client device and a server device as required to achieve real-time recognition of a speech query; and
a natural language engine configured to determine a meaning of said recognized speech query and provide a first response thereto;
a web page routine for presenting one or more web pages to the browser program, wherein data content for said one or more web pages is controlled by said recognized speech query and/or said first response of said natural language engine;
wherein said recognized speech queries can be presented to both said natural language engine as well as to a text based query database for identifying a meaning of said recognized speech query, such that a second response can be provided by said database for at least some recognized speech queries prior to said first response of said natural language engine.
2 Assignments
Litigations
0 Petitions
Accused Products
Abstract
A speech-enabled internet based computing system includes a configurable speech recognition engine used for interacting with content on a web accessible page. The speech recognition engine is distributed across a client and server architecture, and is adaptive so that speech processing operations can be allocated as needed between the two. This allows for support for client devices having differing computing capabilities. Natural language operations can also be supported as desired. A user can thus interact with a web page and select items of interest using speech as a mode of input. Dynamic grammars can assist in the recognition operations to improve speed and comprehension.
464 Citations
10 Claims
-
1. A system for enabling a browser program to interact with a website using speech utterances, the system comprising:
-
a speech recognition engine configured to generate a recognized speech query from an utterance; said speech recognition engine being further configurable such that speech processing operations can be distributed between a client device and a server device as required to achieve real-time recognition of a speech query; and a natural language engine configured to determine a meaning of said recognized speech query and provide a first response thereto; a web page routine for presenting one or more web pages to the browser program, wherein data content for said one or more web pages is controlled by said recognized speech query and/or said first response of said natural language engine; wherein said recognized speech queries can be presented to both said natural language engine as well as to a text based query database for identifying a meaning of said recognized speech query, such that a second response can be provided by said database for at least some recognized speech queries prior to said first response of said natural language engine. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
Specification