Indefinite speech inputs

• US 9,165,566 B2
• Filed: 01/24/2013
• Issued: 10/20/2015
• Est. Priority Date: 01/24/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Klein, Christian, Wygonik, Gregg
• Primary Examiner(s): PULLIAS, JESSE SCOTT
• Application Number:
  US13/749,431
• Publication Number:
  US 20140207446A1
• Time in Patent Office: 999 Days
• Field of Search: 704/275, 704231-257
• US Class Current: 1/1
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 21/10 Transforming into visible information

Abstract

Embodiments are disclosed that relate to the use of speech inputs including indefinite quantitative terms as computing device inputs. For example, one disclosed embodiment provides a method of operating a computing device, the method including receiving a speech input comprising an indefinite quantitative term, determining a definite quantity corresponding to the indefinite quantitative term, and applying the definite quantity to an action performed via the computing device in response to the speech input.

Claims

1. A method of operating a computing device, the method comprising:

receiving a speech input comprising an indefinite quantitative term;

determining a mapping of the indefinite quantitative term to a first definite quantity;

applying the first definite quantity to an action performed via the computing device in response to the speech input;

receiving a follow-up speech input that requests performance of an additional quantity of the action performed; and

modifying the mapping of the indefinite quantitative term to a second definite quantity based upon the follow-up speech input.

2. The method of claim 1, wherein the action is specified by the speech input, and wherein the indefinite quantitative term comprises a parameter for the action.

3. The method of claim 1, further comprising receiving a previous speech input and storing information regarding the previous speech input for use in disambiguating the follow-up speech input.

4. The method of claim 1, wherein the speech input comprises a composite speech input that further comprises an input received via a second input mode.

5. The method of claim 4, wherein the speech input comprises no specified action, and further comprising determining an action based on a state of an application currently in use.

6. The method of claim 1, wherein the action comprises an action performed to control playback of a media item.

7. The method of claim 1, wherein the action comprises an action performed to control the display of information.

8. A computing device, comprising:

a logic subsystem configured to execute instructions; and

a data storage subsystem comprising instructions stored thereon that are executable by the logic subsystem to

receive a speech input comprising an indefinite quantitative term,

determine a mapping of the indefinite quantitative term to a first definite quantity,

apply the first definite quantity to an action performed via the computing device in response to the speech input,

receive a follow-up speech input that requests performance of an additional quantity of the action performed, and

modify the mapping of the indefinite quantitative term to a second definite quantity.

9. The computing device of claim 8, wherein the action is specified by the speech input, and wherein the indefinite quantitative term comprises a parameter for the action.

10. The computing device of claim 8, wherein the speech input is a follow-up speech input that follows a previous speech input and that requests performance of an additional quantity of an action specified by the previous speech input.

11. The computing device of claim 10, wherein the instructions are further executable to modify a mapping of the indefinite quantitative term based upon the follow-up speech input.

12. The computing device of claim 8, wherein the speech input comprises a composite speech input that further comprises an input received via a second input mode.

13. A method of operating a computing device, the method comprising:

receiving a composite user input comprising a speech input and a non-speech input, one of the speech input and the non-speech input requesting an action and another of the speech input and the non-speech input providing an indefinite quantitative term related to the action requested;

determining a definite quantity corresponding to the indefinite quantitative term; and

applying the definite quantity to an action performed in response to the speech input.

14. The method of claim 13, wherein the speech input requests the action and the non-speech input specifies the indefinite quantitative term.

15. The method of claim 14, further comprising receiving a follow-up input requesting an additional quantity of the action, and in response performing the additional quantity of the action and modifying a mapping of the indefinite quantitative term based upon the follow-up speech input.

16. The method of claim 15, wherein the follow-up input comprises a speech input.

17. The method of claim 13, wherein the non-speech input requests the action and the speech input specifies the indefinite quantitative term.

18. The method of claim 13, wherein the non-speech input comprises one or more of a gesture and a posture.