Selective confirmation for execution of a voice activated user interface

• US 8,694,322 B2
• Filed: 10/21/2005
• Issued: 04/08/2014
• Est. Priority Date: 08/05/2005
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation), Alcatel SA (Nokia Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Snitkovskiy, Alex G., Mowatt, David, Andrew, Felix G. T. I., Dewar, Robert Edward, Scholz, Oliver
• Primary Examiner(s): Desir, Pierre-Louis
• Assistant Examiner(s): Serrou, Abdelali
• Application Number:
  US11/256,120
• Publication Number:
  US 20070033054A1
• Time in Patent Office: 3,091 Days
• Field of Search: 704/275, 704/251, 704/E17.016, 704/273, 704/270, 704/E17.011
• 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

Abstract

A voice-activated user interface for an application is described. The voice activated user interface invokes a speech recognition component to recognize audio input from a user. If the audio input is a command, then a validation component is invoked to determine whether to validate the command prior to execution.

Claims

1. A computer system comprising:

a processor;

a computer readable storage media storing instructions which, when executed by the processor, configure the computer system to;

identify a plurality of user selectable tasks or functions for one or more active applications or components;

provide a grammar corresponding to the plurality of user selectable tasks or functions;

recognize, using the grammar, a received audio command corresponding to implementation of a particular one of the plurality of user selectable tasks or functions;

access information in a data store separate from the grammar, wherein said information includes a list of commands and identifies, for each of the commands in the list of commands, one or more of the plurality of user selectable tasks or functions for which the command should be validated, and wherein at least one command in the list of commands has a first one of the user selectable tasks or functions for which the command is to be validated and the same at least one command has a second one of the user selectable tasks or functions for which the command is not to be validated;

output a validation prompt to request validation if the audio command matches at least one command in the data store and the information in the data store indicates that the at least one matched command should be validated.

2. The system of claim 1 wherein the data store includes a list of destructive commands.

3. The system of claim 2 wherein all commands in the list of commands are monosyllabic.

4. The system of claim 1 wherein the instructions configure the computer system to:

invoke a user interface to output the validation prompt to the user to confirm execution of the audio command.

5. The system of claim 1 wherein the instructions configure the computer system to:

output one of an audio prompt or text prompt to confirm implementation of the audio command.

6. The system of claim 1 and further comprising an audio input device, wherein the instructions configure the computer system to:

recognize the audio command from an audio input from the audio input device.

7. A hardware computer readable storage medium storing instructions which, when implemented by a computer, perform a method comprising:

displaying a user interface for an active application that includes one or more user selectable tasks or functions;

receiving an audio input from an audio input device and outputting an audio command corresponding to a user selected task or function of the active application;

recognizing the audio command corresponding to the user selected task or function; and

receiving the audio command and identity of the active application and retrieving, from a validation data store, a list of commands and information identifying one or more applications of a plurality of different applications in which each of the commands requires validation, wherein at least one command in the list of commands has a first application for which the command is to be validated and the same at least one command has a second application for which the command is not to be validated;

determining whether the audio command requires validation by comparing the audio command to the list of commands and comparing the identity of the active application to the information retrieved from the validation data store identifying the one or more applications; and

outputting a validation prompt or request to the user if the audio command requires validation.

8. The hardware computer readable storage medium of claim 7 wherein the data store includes a list of destructive commands requiring validation.

9. The hardware computer readable storage medium of claim 8 wherein all of the destructive commands of the data store are monosyllabic.

10. The hardware computer readable storage medium of claim 7, the method comprising prompting the user to confirm implementation of the audio command if the audio command requires validation.

17. The hardware computer readable storage medium of claim 7, the method comprising providing a grammar to the speech recognition component separate from the validation store wherein the grammar includes words or phrases associated with the one or more user selectable tasks or functions of the user interface.

19. The hardware computer readable storage medium of claim 7 wherein the command in the validation data store include one command that requires validation in one instance and another command that requires validation in a different instance.

11. A computer implementable method comprising:

providing a user interface for an active application or component;

receiving audio input from an audio input device;

using a speech recognition component to recognize a user command from the audio input to implement a given task or function of the user interface;

accessing a data store having a plurality of records, each record pertaining to a particular command and identifying for the particular command one or more tasks or functions for which the particular command should be validated, wherein the data store identifies that the recognized user command requires validation for a first task or function and the same recognized user command does not require validation for a second task or function of the user interface;

identifying, using a computer processor, a record of the plurality of records pertaining to the recognized user command and determining whether to validate the recognized user command based on the record; and

outputting a validation option for the recognized user command if the recognized user command requires validation.

12. The method of claim 11 wherein the plurality of records in the data store comprise monosyllabic commands.

13. The method of claim 11 and comprising:

receiving input in response to a “

yes” and

“

no”

validation option to confirm execution of the user command.

14. The method of claim 11 wherein the output validation option is one of an audio or text prompt.

15. The method of claim 11 and further comprising:

generating a data store record for a command requiring validation based upon feedback from a user.

16. The method of claim 11 and further comprising:

using an application to dynamically populate the data store with the commands requiring validation for the application.

18. The method of claim 11 and comprising:

generating a grammar for the speech recognition component utilizing tasks or functions of the user interface for the active application or component; and

using the grammar to recognize the user command from the audio input.