Centralized method and system for clarifying voice commands

• US 8,942,985 B2
• Filed: 11/16/2004
• Issued: 01/27/2015
• Est. Priority Date: 11/16/2004
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Mowatt, David, Chambers, Robert L., Andrew, Felix G. T. I.
• Primary Examiner(s): Dorvil, Richemond
• Assistant Examiner(s): ORTIZ SANCHEZ, MICHAEL
• Application Number:
  US10/990,345
• Publication Number:
  US 20060106614A1
• Time in Patent Office: 3,724 Days
• Field of Search: 704/270, 704/275
• 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 15/18 using natural language modelling
• 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
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A method and system for facilitating centralized interaction with a user includes providing a recognized voice command to a plurality of application modules. A plurality of interpretations of the voice command are generated by at least one of the plurality of application modules. A centralized interface module visually renders the plurality of interpretations of the voice command on a centralized display. An indication of selection of an interpretation is received from the user.

Claims

1. A computer-implemented method of facilitating centralized interaction with a user, the method comprising:

providing a recognized voice command to a plurality of application modules for execution;

receiving a plurality of possible interpretations of the recognized voice command when at least one of the application modules is unable to execute the recognized voice command because the execution of the recognized voice command is ambiguous in that the recognized voice command could execute more than one action in one of the plurality of application modules, the plurality of possible interpretations are generated by and received from each of the plurality of application modules that are affected;

visually rendering the plurality of possible interpretations of the voice command on a centralized display; and

receiving an indication of selection of an interpretation from the user.

2. The method of claim 1, wherein visually rendering the plurality of interpretations comprises visually rendering the plurality of interpretations in a list, each of the plurality of interpretations having a corresponding numerical identifier.

3. The method of claim 2, wherein receiving an indication of selection of an interpretation comprises receiving a speech signal indicating the numerical identifier that corresponds to the selected interpretation.

4. The method of claim 2, wherein receiving an indication of selection of an interpretation comprises receiving an input device signal indicating the numerical identifier that corresponds to the selection of interpretation.

5. The method of claim 1, further comprising visually rendering an alternative that allows the user to choose to respeak the voice command.

6. The method of claim 5, further comprising visually rendering a plurality of refreshed interpretations when the user chooses to respeak the voice command.

7. The method of claim 1, further comprising visually rendering an alternative that allows the user to choose to create a new interpretation that is not included in the plurality of interpretations.

8. The method of claim 7, wherein allowing the user to choose to create a new interpretation further comprises receiving an audible spelling of the new interpretation.

9. The method of claim 1, wherein the centralized display comprises a centralized panel that is displayed in a consistent location on a computing device display.

10. The method of claim 1, further comprising visually rendering a list of alternative spellings for a misrecognized utterance on the centralized display.

11. The method of claim 1, further comprising visually rendering feedback from the plurality of application modules on the centralized display.

12. The method of claim 1, wherein the execution of the voice command is ambiguous to the plurality of application modules if the recognized voice command could execute an action in more than one of the application modules.

13. The method of claim 1, wherein the execution of the recognized voice command is ambiguous to the plurality of application modules when more than one instance of one of the application modules is open and it is unclear which instance of the one application module the recognized voice command is referencing.

14. A computer-implemented system for facilitating centralized interaction with a user, the system comprising:

a plurality of application modules configured to receive commands for executing various actions;

an audio capture module configured to capture a voice command;

a grammar including a plurality of commands that correspond to commands that the plurality of application modules can receive for executing the various actions and a plurality of alternative forms of the plurality of commands, each of the plurality of alternative forms has the same definition as one of the plurality of commands, but is in a different form;

a speech recognizer configured to recognize the voice command by accessing the plurality of commands and the plurality of alternative forms of the plurality of commands in the grammar;

a centralized interface module configured to;

send the recognized voice command to each of the plurality of application modules for execution;

visually render a plurality of possible interpretations of the recognized voice command received from at least one of the plurality of application modules when the at least one of the plurality of application modules is unable to execute the recognized voice command because the recognized voice command is ambiguous; and

receive an indication from the user of selection of one of the plurality of possible interpretations for executing the voice command.

15. The computer-implemented system of claim 14, wherein the centralized interface module is adapted to visually render an alternative that allows the user to choose to respeak the voice command.

16. The computer-implemented system of claim 14, wherein the centralized interface module is adapted to visually render an alternative that allows the user to choose to create a voice command that is not visually rendered in the list of interpretations.

17. The computer-implemented system of claim 14, wherein the centralized interface module is adapted to visually render a list of alternative phrases for a dictated phrase that includes a recognition error.

18. A computer-implemented method of facilitating centralized interaction with a user, the method comprising:

capturing a voice command;

recognizing the voice command by accessing a grammar including a plurality of recognizable commands that correspond to commands that a plurality of application modules can receive for executing various actions;

sending the recognized voice command to the plurality of application modules for execution;

determining that there is ambiguity in which application module to execute the command or how to execute the recognized voice command in a single application module;

visually rendering a list of possible interpretations of the recognized voice command on a centralized display, the list of possible interpretations generated by and received from the at least one of the plurality of application modules; and

receiving an indication from the user of selection of one of the interpretations.

19. The method of claim 18, wherein the list of interpretations are based on a notion that more than one instance of an application is operating.