Speech Recognition System With Support For Variable Portable Devices

• US 20070179789A1
• Filed: 04/09/2007
• Published: 08/02/2007
• Est. Priority Date: 11/12/1999
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Ian M. Bennett
• Inventors: Bennett, Ian
• Granted Patent: US 7,698,131 B2
• Time in Patent Office: Days
• US Class Current: 704/270.100
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access

Abstract

A speech-enabled internet based computing system includes a configurable speech recognition engine which allows support for client devices having differing computing capabilities. Natural language operations can also be supported as desired.

Claims

1. A speech-enabled internet based computing system comprising:

a speech recognition engine configured to generate a recognized speech query from an utterance;

said speech recognition engine being further configured to distribute speech processing operations between a portable client device and a server device on a device-by-device basis, such that a plurality of portable client devices having differing computing capabilities can be supported;

wherein individual ones of said plurality of portable client devices can be configured to perform at least part of said speech processing operations to generate said recognized speech query;

a web page having a list of items, at least some of said list of items being selectable through a browser on said portable client device based on said recognized speech query.

2. The speech-enabled internet based computing system of claim 1, wherein said website is adapted so that the user can navigate and locate information of interest using said speech query.

3. The speech-enabled internet based computing system of claim 1, wherein said list of items include products and/or services.

4. The speech-enabled internet based computing system of claim 1, wherein said web page is implemented at least in part in HTML or as a Java applet.

5. The speech-enabled internet based computing system of claim 1, wherein said speech-enabled internet based computing system is further adapted to respond to a speech query concerning said list of items by returning a text or speech articulated response.

6. The speech-enabled internet based computing system of claim 1, wherein said speech-enabled internet based computing system is further adapted to interact on a real-time basis in response to one or more continuous speech queries.

7. The speech-enabled internet based computing system of claim 1, wherein the speech-enabled internet based computing system also controls an interactive character agent presented to the user for assisting in handling said speech query.

8. The speech-enabled internet based computing system of claim 7, wherein said interactive character agent is adapted to have configurable perception parameters based on characteristics of a portable device.

9. The speech-enabled internet based computing system of claim 1 wherein respective speech processing operations to be performed by the client platform and the server computing system are specified by an initialization routine.

10. The speech-enabled internet based computing system of claim 1 wherein the server device transfers speech related data for the web page using a hypertext transfer protocol (HTTP) and a format which includes an embedded NULL character.

11. The speech-enabled internet based computing system of claim 1, wherein the speech recognition engine stores calibration configuration data pertaining to calibrating speech and silence components of a speech utterance for each portable device.

12. The speech-enabled internet based computing system of claim 1 wherein the server device is further configured to perform a natural language processing operation on said recognized speech query to recognize a meaning of a sentence of words contained therein.

13. A speech-enabled internet based computing system comprising:

a speech recognition engine configured to generate a recognized speech query from an utterance;

said speech recognition engine being further configured to distribute speech processing operations between a portable client device and a server device on a device-by-device basis, such that a plurality of portable client devices having differing computing capabilities can be supported;

wherein individual ones of said plurality of portable client devices can be configured to perform at least part of said speech processing operations to generate said recognized speech query;

said speech recognition engine being further configured with noise calibration data for each of said plurality of portable client devices;

an Internet accessible page having a list of items, wherein content for at least some of said list of items is selectable from a database based on said recognized speech query.

14. The system of claim 13, wherein said speech query is recognized by forming a concatenation of words and/or phrases derived from said speech query and using said concatenation as a search query for said database.

15. The system of claim 13 wherein said speech recognition engine is also configured to dynamically change a speech recognition grammar based on input provided by a user to selections available within said page.

16. The system of claim 13 wherein multiple speech grammars are available and selectable within the Internet accessible page, and such that speech input provided by the user for an item within the page using a first grammar dynamically controls which one of a plurality of second grammars is loaded for speech recognition of subsequent speech input by the user.

17. The system of claim 13 further including an electronic conversational agent adapted to interact with a user and mimic behavior of a human agent through a native language interactive real-time dialog session with the user.

18. The system of claim 13, wherein the server device transfers speech related data using a hypertext transfer protocol (HTTP) and using a format which includes a predetermined NULL character.

19. The system of claim 13, wherein the server device automatically configures a number of speech processing operations.

20. A speech-enabled internet based computing system comprising:

a speech recognition engine configured to generate a recognized speech query from an utterance;

said speech recognition engine being further configured to distribute speech processing operations between a portable client device and a server device on a device-by-device basis, such that a plurality of portable client devices having differing computing capabilities can be supported;

wherein individual ones of said plurality of portable client devices can be configured to perform at least part of said speech processing operations to generate said recognized speech query;

said speech recognition engine being further configured with noise calibration data for each of said plurality of portable client devices;

wherein said calibration data is collected over a network from different ones of said plurality of portable client devices;

a World-Wide Web (WWW) accessible page having a list of items selectable with a WWW browser, wherein content for at least some of said list of items is selectable from a database based on said recognized speech query.