Audio triggers based on context

1. A method comprising:

determining, by a first computing device, a context of the first computing device, the context including an indication that a second computing device is proximate to the first computing device;

determining, by the first computing device, based at least in part on the context, a subset of contextual audio triggers from a plurality of contextual audio triggers, each contextual audio trigger from the plurality of contextual audio triggers usable to initiate interaction with the first computing device, wherein each contextual audio trigger from the subset of contextual audio triggers is associated with a respective operation of the first computing device and with the context of the computing device, and wherein one of the subset of contextual audio triggers is associated with a first operation to cause the second computing device to perform a second operation;

receiving, by the first computing device, audio data; and

responsive to determining that a portion of the audio data corresponds to a particular contextual audio trigger from the subset of contextual audio triggers, performing, by the first computing device, the respective operation associated with the particular contextual audio trigger.

2. The method of claim 1 , further comprising:

responsive to determining that the portion of the audio data does not correspond to any contextual audio trigger from the subset of contextual audio triggers, determining whether the portion of the audio data corresponds to a default audio trigger usable to initiate interaction with the first computing device; and

responsive to determining that the portion of the audio data corresponds to the default audio trigger, entering an audio input mode.

3. The method of claim 1 , wherein determining the subset of contextual audio triggers comprises:

sending, by the first computing device, to a computing system, at least an indication of the context; and

receiving, by the first computing device and from the computing system, an indication of at least one candidate audio command, wherein the at least one candidate audio command was previously used at least at a threshold frequency in the context.

4. The method of claim 1 ,

wherein the context includes an indication of an application executing at the first computing device, and

wherein each contextual audio trigger from the subset of contextual audio triggers is associated with a respective operation performed by the application executing at the first computing device.

5. The method of claim 1 ,

wherein the context includes an indication of an application executing at the first computing device,

wherein the application executing at the first computing device comprises an alarm clock application, and

wherein at least one contextual audio trigger from the subset of contextual audio triggers is associated with one or more of scheduling an alarm notification, dismissing the alarm notification, or postponing the alarm notification.

6. The method of claim 1 ,

wherein the context includes an indication of an application executing at the second computing device,

wherein the application executing at the second computing device comprises a navigation application, and

wherein at least one contextual audio trigger from the subset of contextual audio triggers is associated with an operation to cause the second computing device to perform one or more of creating a navigation route, removing the navigation route, pausing the navigation route, progressing to a next instruction of the navigation route, regressing to a previous instruction of the navigation route, adding a destination to the navigation route, or removing the destination from the navigation route.

7. The method of claim 1 , wherein the context further includes an indication of at least one of: a speed at which the first computing device is travelling, a time of day, an alert recently output at the first computing device, a notification recently output at the first computing device, an application executing at the first computing device, or a location of the first computing device.

8. The method of claim 1 , wherein the second operation comprises unlocking a lock operatively coupled to the second computing device.

9. A first computing device, comprising:

at least one processor; and

at least one module, operable by the at least one processor, to:

determine a context of the first computing device, the context including an indication that a second computing device is proximate to the first computing device;

determine, based at least in part on the context, a subset of contextual audio triggers from a plurality of contextual audio triggers, each contextual audio trigger from the plurality of contextual audio triggers usable to initiate interaction with the first computing device, wherein each contextual audio trigger from the subset of contextual audio triggers is associated with a respective operation of the first computing device and with the context of the first computing device, and wherein one of the subset of contextual audio triggers is associated with a first operation to cause the second computing device to perform a second operation;

receive audio data; and

responsive to determining that a portion of the audio data corresponds to a particular contextual audio trigger from the subset of contextual audio triggers, perform the respective operation associated with the particular contextual audio trigger.

10. The first computing device of claim 9 , wherein the at least one module is further operable by the at least one processor to:

responsive to determining that the portion of the audio data does not correspond to any contextual audio trigger from the subset of contextual audio triggers, determine whether the portion of the audio data corresponds to a default audio trigger; and

responsive to determining that the portion of the audio data corresponds to the default audio trigger, enter an audio input mode.

11. The first computing device of claim 9 , wherein the at least one module operable to determine the subset of contextual audio triggers is operable by the at least one processor to:

send, to a computing system, at least an indication of the context; and

receive, from the computing system, an indication of at least one candidate audio command, wherein the at least one candidate audio command was previously used at least at a threshold frequency in the context.

12. The first computing device of claim 9 ,

wherein the context includes an indication of an application executing at the first computing device, and

wherein each contextual audio trigger from the subset of contextual audio triggers is associated with a respective operation performed by the application executing at the first computing device.

13. The first computing device of claim 9 ,

wherein the context includes an indication of an application executing at the first computing device;

wherein the application executing at the first computing device comprises an alarm clock application, and

wherein at least one contextual audio trigger from the subset of contextual audio triggers is associated with one or more of scheduling an alarm notification, dismissing the alarm notification or postponing the alarm notification.

14. The first computing device of claim 9 ,

wherein the context includes an indication of an application executing at the second computing device;

wherein the application executing at the second computing device comprises a navigation application, and

wherein at least one contextual audio trigger from the subset of contextual audio triggers is associated with an operation to cause the second computing device to perform one or more of creating a navigation route, removing the navigation route, pausing the navigation route, progressing to a next instruction of the navigation route, regressing to a previous instruction of the navigation route, adding a destination to the navigation route, and or removing the destination from the navigation route.

15. The first computing device of claim 9 , wherein the context further includes an indication of at least one of: a speed at which the first computing device is travelling, a time of day, an alert recently output at the first computing device, a notification recently output at the first computing device, an application executing at the first computing device, or a location of the first computing device.

16. A computer-readable storage device encoded with instructions that, when executed, cause at least one processor of a first computing device to:

determine a context of the first computing device, the context including an indication that a second computing device is proximate to the first computing device;

determine, based at least in part on the context, a subset of contextual audio triggers from a plurality of contextual audio triggers, each contextual audio trigger from the plurality of contextual audio triggers usable to initiate interaction with the first computing device, wherein each contextual audio trigger from the subset of contextual audio triggers is associated with a respective operation of the first computing device and with the context of the first computing device, and wherein one of the subset of contextual audio triggers is associated with a first operation to cause the second computing device to perform a second operation;

receive audio data; and

responsive to determining that a portion of the audio data corresponds to a particular contextual audio trigger from the subset of contextual audio triggers, perform the respective operation associated with the particular contextual audio trigger.

17. The computer-readable storage device of claim 16 , further encoded with instructions that, when executed, cause the at least one processor to:

responsive to determining that the portion of the audio data does not correspond to any contextual audio trigger from the subset of contextual audio triggers, determine whether the portion of the audio data corresponds to a default audio trigger usable to initiate interaction with the first computing device; and

responsive to determining that the portion of the audio data corresponds to the default audio trigger, enter an audio input mode.

18. The computer-readable storage device of claim 16 , wherein the instructions that cause the at least one processor to determine the subset of contextual audio triggers comprise instructions that cause the at least one processor to determine the subset of contextual audio triggers based at least in part on a frequency with which the plurality of contextual audio triggers were previously used in the context.