Voice activated apparatus for accessing information on the World Wide Web

• US 7,020,609 B2
• Filed: 03/16/2001
• Issued: 03/28/2006
• Est. Priority Date: 04/10/1995
• Status: Expired due to Fees

• Current Assignee: Texas Instruments, Inc.
• Original Assignee: Texas Instruments, Inc.
• Inventors: Hemphill, Charles T., Thrift, Philip R.
• Primary Examiner(s): CHAWAN, VIJAY B
• Application Number:
  US09/811,231
• Publication Number:
  US 20010034603A1
• Time in Patent Office: 1,838 Days
• Field of Search: 704/275, 704/257, 704/235, 704/251, 704/270, 704/270.1, 704/231
• US Class Current: 704/270.1
• CPC Class Codes: G06F 16/957 Browsing optimisation, e.g. caching or content distillation
• CPC Class Codes: G10L 15/193 Formal grammars, e.g. finite state automata, context free grammars or word networks
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

This is a voice activated Hypermedia system using grammatical metadata, the system comprising: a speech user agent; a browsing module; and an information resource. The system may include: embedded intelligence in hypermedia source; a means for processing the actions of a user based on the embedded intelligence; a means for returning a result of the actions to the user. In addition, the hypermedia source maybe a HTML page or an instructional module for communicating allowed actions by a user. The system may also include embedded intelligence as a grammar or reference to a grammar. The grammar may be dynamically added to a speech recognizer. In addition, the actions can come from a speech recognizer. Furthermore, the system may include voice activated hypermedia links and intelligent modules that process information from the information resources for allowing actions from the user. Other devices, systems and methods are also disclosed.

Claims

1. An apparatus, comprising:

a speech user agent that dynamically creates vocabulary, grammar and actions; and

a browsing module for the world wide web being responsive to said speech user agent, said speech user agent facilitating voice activation of said browsing module to access an information resource on the world wide web.

2. The apparatus of claim 1, wherein said access of said information resource is accomplished in part through use of a grammar embedded in said information resource.

3. The apparatus of claim 2, wherein said information resource is an HTML page.

4. The apparatus of claim 2, wherein said embedded grammar is a smart page grammar.

5. The apparatus of claim 2, wherein said embedded grammar is a reference to a grammar located in said information resource.

6. The apparatus of claim 2, wherein said grammar is dynamically added to a speech recognizer.

7. The apparatus of claim 2, further including a means for processing the verbal directions of a user based on said grammar.

8. The apparatus of claim 7, wherein said actions come from a speech recognizer.

9. The apparatus of claim 7, further including a means for returning a result of said verbal directions to said user.

10. The apparatus of claim 1, further including an instructional module for communicating allowed actions by a user.

11. The apparatus of claim 1, further including a means for extracting a grammar from a hypermedia source on said information resource for future reference to said source.

12. The apparatus of claim 11, further including a means for automatically producing an intelligent grammar from said information resource.

13. The apparatus of claim 12, further including a means for processing said grammar to produce a reference to said hypermedia source.

14. The apparatus of claim 1, wherein said apparatus further includes a means for tokenizing a title for addition into said grammar.

15. The apparatus of claim 1, wherein said apparatus includes a means for dynamically adding said grammar to a speech recognizer.

16. An apparatus, comprising:

a speech user agent for accessing a browsing module for the world wide web, said speech user agent dynamically creates vocabulary, grammar and actions to enable said browsing module to access an information resource on the world wide web.

17. A method, comprising:

embedding voice activated control information in HTML pages as delivered on the World Wide Web, wherein said voice control information is encoded in a grammar language and is interpreted by a Web client user-agent that translates user utterances into client actions.

18. An apparatus, comprising:

a speech user agent that dynamically creates vocabulary and grammar; and

a browsing module for the world wide web being responsive to said speech user agent, said speech user agent facilitating voice activation of said browsing module to access an information resource on the world wide web.

19. An apparatus, comprising:

a speech user agent for accessing a browsing module for the world wide web, said speech user agent dynamically creates vocabulary and grammar to enable said browsing module to access an information resource on the world wide web.

20. An apparatus, comprising:

a speech user agent enabled to access a speakable Hotlist; and

a browsing module for the world wide web being responsive to said speech user agent, said speech user agent facilitating voice activation of said browsing module to access an information resource on the world wide web.

21. The apparatus of claim 20, wherein said speakable Hotlist comprises grammars associated with respective URLs.

22. The apparatus of claim 20, wherein said speakable Hotlist is modifiable by voice command.

23. The apparatus of claim 22, wherein the voice command is a phrase that adds a page to the Hotlist.

24. The apparatus of claim 23, wherein adding a page to the Hotlist comprises adding the title of the page as a default grammar and associating that grammar with a current URL.

25. A method of extracting link names from a page of a speakable Hotlist, comprising the steps of:

speaking a link name;

retrieving the link name from the page;

identifying token(s) in the link name;

creating pronunciation grammar(s) for the token(s);

creating grammars for the link token(s);

creating a grammar for all the links on the page; and

adding the created grammars to the current set known by a speech recognizer.

26. The method of claim 25, wherein said link name is a link name/URL pair.