System and method for voice controlled video screen display

• US 5,890,123 A
• Filed: 06/05/1995
• Issued: 03/30/1999
• Est. Priority Date: 06/05/1995
• Status: Expired due to Term

• Current Assignee: Alcatel-Lucent USA, Inc. (Nokia Corporation)
• Original Assignee: Lucent Technologies, Inc. (Nokia Corporation)
• Inventors: Brown, Michael Kenneth, Buntschuh, Bruce Melvin
• Primary Examiner(s): Dorvil, Richemond
• Application Number:
  US08/460,955
• Time in Patent Office: 1,394 Days
• Field of Search: 395/2.44, 395/2.84, 395/2.79, 395/12, 395/2.4, 704/235, 704/231, 704/270, 704/272, 704/275, 704/9, 704/200
• US Class Current: 704/270.1
• CPC Class Codes: G06F 3/16 Sound input; Sound output speech processing G10L
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

A system and method for a voice controlled video screen display system are provided. The voice controlled system is useful for providing "hands-free" navigation through various video screen displays such as the World Wide Web network and interactive television displays. During operation of the system, language models are provided from incoming data in applications such as the World Wide Web network.

Claims

1. A voice-interactive video screen display system comprising:

means for recognizing a set of data links, each data link associated with visual information concurrently displayed on a video scrcen;

means for recognizing voiced ulterances corresponding to the displayed visual information on said video screen and the associated data link, and generating corresponding natural language text, said visual information having been diplayed prior to the voiced utterances being spoken; and

means for evaluating said natural language text and converting said natural language text to programming commands for changing the video screen display in accordance with said data link corresponding to said recognized voiced utterances.

2. A system according to claim 1, wherein said video screen display is selected from the group consisting of a computer monitor, a television screen, automatic teller machine screen and telephone screen display.

3. A system according to claim 1, wherein said data links include software text formatting directives.

4. A system according to claim 1, wherein said means for recognizing voiced utterances receives signals from a microphone positionable remote from a location of said system.

5. A system according to claim 1, wherein said means for recognizing data links interprets data links from software for accessing the World Wide Web network.

6. A system according to claim 1, wherein said means for recognizing data links interprets data links of at least one document displayed on said video screen display.

7. A system according to claim 1, wherein said means for recognizing data links interprets data links of at least one document stored in memory.

8. A system according to claim 1, wherein said programming commands produced by said means for evaluating natural language text direct the system to access a document for display on said video screen.

9. A device for accessing pages of a video screen display from a data connection comprising:

means for recognizing a set of data links, each associated with visual information concurrently displayed on at least a portion of a video screen display;

means for providing grammar corresponding to said data links of said video screen display;

means for recognizing speech and identifying whether the speech corresponds to said grammar associated with any one of said data links and th associated visual information already displayed; and

means for transmitting a signal representative of a new video screen display if the speech corresponds to said any one data link, said new video screen display being associated with the one data link.

10. A device according to claim 9, wherein said means for recognizing a set of data links and said means for providing grammar corresponding to said data links are selected from the group consisting of a compiler, an interpreter and an evaluator.

11. A device according to claim 9, wherein said video screen display is selected from the group consisting of a computer monitor, a television screen, automatic teller machine screen and telephone screen display.

12. A device according to claim 9, wherein said data links include software text formatting directives.

13. A device according to claim 9, wherein said means for recognizing a set of data links interprets data links of software for accessing the World Wide Web network.

14. A device according to claim 9, wherein said means for recognizing a set of data links interprets data links of a document displayed on said video screen display.

15. A device according to claim 9, wherein said means for recognizing a set of data links interprets data links of at least one document stored in memory.

16. A method for accessing pages of a video screen display from a data connection comprising:

recognizing a set of data links, each associated with visual information concurrently displayed on at least a portion of a video screen display;

producing grammar corresponding to said data links of said video screen display;

recognizing speech and identifying whether the speech corresponds to said grammar associated with any one of said data links and the associated visual information already displayed; and

if the speech corresponds to one of said data links, transmitting a signal representative of a new video screen display associated with the one data link.

17. A method according to claim 16, wherein said step of recognizing a set of data links includes accessing the World Wide Web network and interpreting data links of at least one document of the World Wide Web network.

18. A method according to claim 16, wherein said step of recognizing a set of data links includes interpreting data links displayed on a video screen.

19. A method according to claim 16, wherein said step of recognizing a set of data links includes interpreting data links of at least one document stored in memory.

20. A method according to claim 16, further including the steps of:

merging said grammar produced in said producing step with a base grammar associated with a portion of said video display;

said step of recognizing speech further including identifying whether said speech corresponds to either said base grammar or said produced grammar; and

said step of transmitting further including transmitting a signal representative of a new video screen display associated with said base grammar if said speech corresponds to said base grammar.