Method and apparatus for presenting proximal feedback in voice command systems

• US 6,233,560 B1
• Filed: 12/16/1998
• Issued: 05/15/2001
• Est. Priority Date: 12/16/1998
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Tannenbaum, Alan Richard
• Primary Examiner(s): SMITS, TALIVALDIS IVARS
• Application Number:
  US09/213,857
• Time in Patent Office: 881 Days
• Field of Search: 704/275, 345/347
• US Class Current: 704/275
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

In a voice actuated computer system voice command from an end user relevant to or promoted from a discrete location on a display screen are analyzed by the system. In response, a confirmation area is displayed on the screen at a location functionally related to the analyzed contents and context of the voice input or the screen location the utterance was prompted from. Within the confirmation area the computer interpretation of the utterance is displayed persisting and dissolving at selectively adjustable rates and times. Display of the recognized utterance is thereby placed in a confirmation area at variable locations where the user'"'"'s focus is likely to be. Distractions are avoided associated with a fixed location confirmation area which obscures other content on the display screen and/or destroys end-user focus by requiring the eyes to shift from a location of current interest on the display screen to a different location wherein the confirmation is displayed. Persistence and dissolution time of the confirmation area and associated analyzed voice command displayed therein may vary automatically as a function of the degree of confidence of the voice recognition system that the command was accurately analyzed, and correctly recognized commands are automatically executed after display in the confirmation window.

Claims

1. A method for presenting feedback on a display in a voice command recognition computer system executing a voice recognition application, comprising:

recognizing a speech command;

selecting one of a plurality of positions on said display as a function of said recognized speech command;

displaying feedback at a confirmation area proximal to said one of said positions and corresponding to said command;

extinguishing said feedback at a time after said displaying;

automatically executing said command after said displaying; and

wherein timing of said extinguishing is dynamically selected and wherein said feedback is selected from a group comprising a color change, animation, message, or reducing image on said display.

2. The method of claim 1 further including

determining a confidence factor corresponding to accuracy of said recognizing; and

wherein said time of extinguishing corresponds to said confidence factor.

3. The method of claim 2 including

depicting on said display information corresponding to said speech command at a location on said display;

wherein said speech command corresponds to said information; and

wherein said one of said positions corresponds to said location.

4. The method of claim 2 including

analyzing said speech command;

and

wherein said one of said positions is a function of said analyzing.

5. The method of claim 2 wherein said computer system includes

a graphical user interface on said display and a pointing device;

and

wherein said speech command corresponds to a command displayed on said graphical user interface actuatable by said pointing device.

6. The method of claim 2 wherein said confidence factor and said timing of extinguishing are inversely related.

7. The method of claim 1 further including

recognizing a next speech command;

selecting a next one of a plurality of positions on said display screen as a function of said recognized next speech command; and

displaying next feedback at a next confirmation area proximal to said next one of said positions and corresponding to said next speech command.

8. An apparatus for presenting feedback on a display in a voice command recognition computer system executing a voice recognition application, comprising:

means for recognizing a speech command;

means for selecting one of a plurality of positions on said display as a function of said recognized speech command;

means for displaying feedback at a confirmation area proximal to said one of said positions and corresponding to said command;

means for extinguishing said feedback at a time after said displaying;

means for automatically executing said command after said displaying; and

wherein said timing of said extinguishing is dynamically selected and wherein said feedback is selected from a group comprising a color change, animation, message, or reducing image on said display.

9. The apparatus of claim 8 further including

means for determining a confidence factor corresponding to accuracy of said detecting; and

wherein said time of extinguishing corresponds to said confidence factor.

10. The apparatus of claim 9 including

means for depicting on said display information corresponding to said speech command at a location on said display;

wherein said speech command corresponds to said information; and

wherein said one of said positions corresponds to said location.

11. The apparatus of claim 9 including

means for analyzing said speech command;

and

wherein said one of said positions is a function of said analyzing.

12. The apparatus of claim 9 wherein said computer system includes

a graphical user interface on said display and a pointing device;

and

wherein said speech command corresponds to a command displayed on said graphical user interface actuatable by said pointing device.

13. The apparatus of claim 9 wherein said computer system includes

a graphical user interface on said display and a pointing device;

and

wherein said speech command corresponds to a non-visible command interpreted by an application running on said graphical environment.

14. The apparatus of claim 9 wherein said confidence factor and said timing of extinguishing are inversely related;

and wherein said computer system further includes

a graphical user interface on said display and a pointing device; and

wherein said speech command corresponds to a non-visible command interpreted by an application executing in said graphical user interface.

15. The apparatus of claim 8 further including

means for recognizing a next speech command;

means for selecting a next one of a plurality of positions on said display screen as a function of said recognized next speech command; and

means for displaying next feedback at a next confirmation area proximal to said next one of said positions and corresponding to said next speech command.

16. A program product for presenting feedback on a display in a voice command recognition computer system executing a voice recognition application, comprising:

program code means for recognizing a speech command;

program code means for selecting one of a plurality of positions on said display as a function of said recognized speech command; and

program code means for displaying feedback at a confirmation area proximal to said one of said positions and corresponding to said command;

program code means for extinguishing said feedback at a time after said displaying;

program code means for automatically executing said command after said displaying; and

wherein said timing of said extinguishing is dynamically selected and wherein said feedback is selected from a group comprising a color change, animation, message, or reducing image on said display.

17. The program product of claim 16 further including

program code means for determining a confidence factor corresponding to accuracy of said recognizing a speech command; and

wherein said timing of extinguishing corresponds to said confidence factor.

18. The program product of claim 17 including

program code means for depicting on said display information corresponding to said speech command at a location on said display;

wherein said speech command corresponds to said information; and

wherein said one of said positions corresponds to said location.

19. The program product of claim 17 including

program code means for analyzing said speech command;

and

wherein said one of said positions is a function of said analyzing.

20. The program product of claim 17 wherein said computer system includes

a graphical user interface on said display and a pointing device;

and

wherein said speech command corresponds to a command displayed on said graphical user interface actuatable by said pointing device.

21. The program product of claim 17 wherein said computer system includes

a graphical user interface on said display and a pointing device;

and

wherein said speech command corresponds to a non-visible command interpreted by an application running on said graphical environment.

22. The program product of claim 17 wherein said confidence factor and said timing of extinguishing are inversely related.

23. The program product of claim 16 further including

program code means for recognizing a next speech command;

program code means for selecting a next one of a plurality of positions on said display screen as a function of said recognized next speech command; and

program code means for displaying next feedback at a next confirmation area proximal to said next one of said positions and corresponding to said next speech command.