Web-based voice dialog interface

• US 6,604,075 B1
• Filed: 03/14/2000
• Issued: 08/05/2003
• Est. Priority Date: 05/20/1999
• Status: Expired due to Term

• Current Assignee: Nokia of America Corporation (Nokia Corporation)
• Original Assignee: Lucent Technologies, Inc. (Nokia Corporation)
• Inventors: Brown, Michael Kenneth, Schmult, Brian Carl, Glinski, Stephen Charles
• Primary Examiner(s): Knepper, David D.
• Application Number:
  US09/524,964
• Time in Patent Office: 1,239 Days
• Field of Search: 704/200, 704/231, 704/270, 704/270.1, 704/275, 382/115, 707/5-8, 707/531
• US Class Current: 704/270.1
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

A web-based voice dialog interface for use in communicating dialog information between a user at a client machine and one or more servers coupled to the client machine via the Internet or other computer network. The interface in an illustrative embodiment includes a web page interpreter for receiving information relating to one or more web pages. The web page interpreter generates a rendering of at least a portion of the information for presentation to a user in an audibly-perceptible format. A grammar processing device utilizes interpreted web page information received from the web page interpreter to generate syntax information and semantic information. A speech recognizer processes received user speech in accordance with the syntax information, and a natural language interpreter processes the resulting recognized speech in accordance with the semantics information to generate output for delivery to a web server in conjunction with a voice dialog which includes the user speech and the rendering of the web page(s). The output may be processed by a common gateway interface (CGI) formatter prior to delivery to a CGI associated with the web server.

Claims

1. An apparatus for implementing a web-based voice dialog interface, the apparatus comprising:

a first interpreter for receiving information relating to one or more web pages, the first interpreter generating a rendering of at least a portion of the information for presentation to a user in an audibly-perceptible format;

a grammar processing device having an input coupled to an output of the first interpreter, the grammar processing device utilizing interpreted web page information received from the first interpreter to generate syntax information and semantic information;

a speech recognizer which processes user speech in accordance with the syntax information generated by the grammar processing device; and

a second interpreter having an input coupled to an output of the speech recognizer, the second interpreter processing recognized speech in accordance with the semantics information from the grammar processing device to generate output for delivery to a web server in conjunction with a dialog which includes at least a portion of the rendering and the user speech.

2. The apparatus of claim 1 wherein the grammar processing device comprises a grammar compiler.

3. The apparatus of claim 2 wherein the grammar processing device implements a grammar generation process to generate a grammar specification language which is supplied as input to the grammar compiler.

4. The apparatus of claim 3 wherein the grammar generation process utilizes a thesaurus to expand the grammar specification language.

5. The apparatus of claim 1 wherein the first interpreter comprises a web page interpreter capable of interpreting web pages formatted at least in part using HTML.

6. The apparatus of claim 1 wherein the second interpreter comprises a natural language interpreter.

7. The apparatus of claim 1 wherein the output generated by the second interpreter is further processed by a common gateway interface formatter prior to delivery to the web server.

8. The apparatus of claim 1 wherein the common gateway interface formatter formats the output generated by the second interpreter into a format suitable for a common gateway interface associated with the web server.

9. The apparatus of claim 8 wherein the common gateway interface is coupled to a database management system.

10. The apparatus of claim 1 wherein the first interpreter further generates a client library associated with interpretations of web pages previously performed on a common client machine, the client library including a script language definition of semantic actions.

11. The apparatus of claim 10 further including a client executive program which processes information in the client library for delivery to the web server.

12. The apparatus of claim 1 wherein the web page information is at least partially in an HTML format.

13. The apparatus of claim 12 wherein the first interpreter includes a capability for interpreting a plurality of voice-related HTML tags.

14. The apparatus of claim 1 wherein dialog control is handled by representing a given dialog turn in a single web page.

15. The apparatus of claim 14 wherein a finite state dialog controller is implemented as a sequence of web pages each representing a dialog turn.

16. The apparatus of claim 1 wherein the processing operations of the dialog are associated with an application developed using a dialog application development tool.

17. The apparatus of claim 16 wherein the dialog application development tool comprises an authoring tool which utilizes a grammar specification language to generate output in a web page format for delivery to one or more clients, and parses code to generate a common gateway interface output for delivery to the web server.

18. A method for implementing a web-based voice dialog interface, the method comprising the steps of:

generating a rendering of at least a portion of a set of information relating to one or more web pages received over a network, for presentation to a user in an audibly-perceptible format;

utilizing interpreted web page, information to generate syntax information and semantic information;

processing user speech in accordance with the syntax information; and

processing recognized speech in accordance with the semantics information to generate output for delivery to a web server in conjunction with a dialog which includes at least a portion of the rendering and the user speech.

19. A machine-readable medium for storing one or more programs for implementing a web-based dialog interface, wherein the one or more programs when executed by a processing system carry out the steps of:

generating a rendering of at least a portion of a set of information relating to one or more web pages received over a network, for presentation to a user in an audibly-perceptible format;

utilizing interpreted web page information to generate syntax information and semantic information;

processing user speech in accordance with the syntax information to generate recognized speech; and

processing the recognized speech in accordance with the semantics information to generate output for delivery to a web server in conjunction with a dialog which includes at least a portion of the rendering and the user speech.

20. A processing system comprising:

at least one computer for implementing at least a portion of an web-based voice dialog interface, the interface including;

(i) a first interpreter for receiving information relating to one or more web pages, the first interpreter generating a rendering of at least a portion of the information for presentation to a user in an audibly-perceptible format;

(ii) a grammar processing device having an input coupled to an output of the first interpreter, the grammar processing device utilizing interpreted web page information received from the first interpreter to generate syntax information and semantic information;

(iii) a speech recognizer which processes user speech in accordance with the syntax information generated by the grammar processing device; and

(iv) a second interpreter having an input coupled to an output of the speech recognizer, the second interpreter processing recognized speech in accordance with the semantics information from the grammar processing device to generate output for delivery to a web server in conjunction with a dialog which includes at least a portion of the rendering and the user speech.