Method of interacting through speech with a web-connected server

• US 8,352,277 B2
• Filed: 04/09/2007
• Issued: 01/08/2013
• Est. Priority Date: 11/12/1999
• Status: Expired due to Fees

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Phoenix Solutions Incorporated (CDC Corporation)
• Inventors: Bennett, Ian M.
• Primary Examiner(s): Lerner, Martin
• Application Number:
  US11/733,129
• Publication Number:
  US 20070185717A1
• Time in Patent Office: 2,101 Days
• Field of Search: 704/255, 704/257, 704/258, 704/270, 704/270.1, 704/275, 704/231, 704/251, 704/252, 707/3, 707/6
• US Class Current: 704/270.1
• 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 recognition engine is configured to permit partial or full recognition of an utterance at a client device and/or a server device. 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 content also accessible at 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.

Claims

1. A method of interacting through speech with a web-connected server system using a browser program, the method comprising the steps of:

establishing a connection between a client device and the web-connected server for communicating speech related data;

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

wherein said speech recognition engine can be configured based on a latency requirement specified for said speech query to permit partial or full recognition of said utterance at said client device and/or a server device;

presenting one or more web pages to the browser program, such that data content for said one or more web pages transmitted to the browser program is controlled by said recognized speech query.

2. The method of claim 1 further including a step:

performing a natural language processing operation to compare a limited set of phrases extracted from said recognized speech query with a separate set of phrases extracted from predefined valid queries from users.

3. The method of claim 2, further including a step:

forming a concatenation of words and/or phrases derived from said speech query and using said concatenation as a search query for a database.

4. The method of claim 2 wherein said natural language processing operation can consider words and/or phrases in said recognized speech query which are not in said separate set of phrases.

5. The method of claim 1 further including a step:

providing an interactive electronic character who provides suggestions for queries which the user can articulate.

6. The method of claim 5, further including a step:

configuring said interactive character agent to engage in a dialog of successive questions and answers with the user during an interactive session.

7. The method of claim 1, further including a step:

presenting an interactive character agent to the user in real-time in response to a spoken help command presented while interacting with any web page maintained by the web-connected server.

8. The method of claim 1, further including a step:

configuring said web page as a single page to a browser to allow a user to ask questions concerning any item identified in said database within said single page.

9. The method of claim 1, wherein the server device transfers speech related data for the web page using a hypertext transfer protocol (HTTP).

10. The method of claim 1 further including a step:

dynamically changing a speech recognition grammar based on input provided by a user to selections available within said web page.

11. A method of interacting through speech with a web-connected server system using a browser program, the method comprising the steps of:

establishing a connection between a client device and the web-connected server for communicating speech related data;

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

wherein said variable distributed speech recognition engine can be configured to permit partial or full recognition of said utterance at said client device and/or a server device based on respective resources available to said client device and server device and further considering a latency requirement specified for said speech query;

presenting data content associated with one or more web pages to the browser program, such that data content transmitted to the browser program is controlled by said recognized speech query.

12. The method of claim 11 wherein said data content also can be accessed by a non-speech based input device from said one or more web pages.

13. The method of claim 11 further including a step:

providing an interactive electronic character who provides suggestions for queries which the user can articulate.

14. The method of claim 13, further including a step:

configuring said interactive character agent to engage in a dialog of successive questions and answers with the user during an interactive session.

15. The method of claim 13, further including a step:

configuring perception related parameters of the electronic interactive character based on preference data for said user, including one of a gender, a visual appearance, and/or voice characteristics including one of pitch, volume and/or speed.

16. The method of claim 13 wherein the interactive electronic agent provides responses adjusted for a context experienced by the user.

17. The method of claim 11, further including a step:

forming a concatenation of words and/or phrases derived from said speech query and using said concatenation as a search query for a database.

18. The method of claim 17, wherein a plurality of potential responses from said database are further evaluated by a natural language engine to determine a single best answer.

19. The method of claim 11, wherein said speech recognition engine is distributed between a client device and a server device which receives streaming speech data having reduced latency data content before silence is detected and the utterance is complete.

20. A method of interacting through speech with a web-connected server system using a browser program executing on a client device the method comprising the steps of:

establishing a connection between the client device and the web-connected server for communicating speech related data;

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

wherein said variable distributed speech recognition engine is automatically configured to permit partial or full recognition of said utterance at the client device and/or a server device based on measuring resources available to said client device and server device, and further based on a latency requirement specified for said speech query

presenting content associated with one or more web pages to the browser program, such that data content for said one or more web pages transmitted to the browser program is controlled by said recognized speech query.