Voice onset detection

1. A system comprising:

a wearable head device comprising:

a frame comprising:

a first left eye portion configured to rest at a first height with respect to a user's eye when the frame is worn by the user; and

a second right eye portion configured to rest at a second height with respect to the user's eye when the frame is worn by the user, the second height different from the first height;

a first microphone disposed on the first left eye portion of the frame; and

a second microphone disposed on the second right eye portion of the frame; and

one or more processors configured to perform a method comprising:

receiving, via the first microphone, a first voice audio signal;

determining a first probability of voice activity based on the first voice audio signal;

receiving, via the second microphone, a second voice audio signal;

determining a second probability of voice activity based on the first voice audio signal and the second voice audio signal;

determining whether a first threshold of voice activity is met based on the first probability of voice activity and the second probability of voice activity;

in accordance with a determination that the first threshold of voice activity is met, determining that a voice onset has occurred; and

in accordance with a determination that the first threshold of voice activity is not met, forgoing determining that a voice onset has occurred.

2. The system of claim 1 , wherein the first height is a positive height and the second height is a negative height.

3. The system of claim 2 , wherein the first height and the second height are equal in magnitude.

4. The system of claim 2 , wherein the first height and the second height are unequal in magnitude.

5. The system of claim 1 , wherein the first left eye portion comprises a first corner of the frame and the second right eye portion comprises a second corner of the frame.

6. The system of claim 1 , wherein the first microphone is configured to rest a first distance from a user's mouth, and wherein the second microphone is configured to rest a second distance from the user's mouth, the first distance unequal to the second distance.

7. The system of claim 1 , wherein the method further comprises determining a time offset associated with a difference between the first distance and the second distance, wherein determining the second probability of voice activity based on the first voice audio signal and the second voice audio signal comprises compensating for the time offset.

8. A method comprising:

receiving, via a first microphone of a wearable head device, a first voice audio signal;

determining a first probability of voice activity based on the first voice audio signal;

receiving, via a second microphone of the wearable head device, a second voice audio signal;

combining the first voice audio signal and the second voice audio signal to produce a third voice audio signal;

determining a second probability of voice activity based on the third voice audio signal;

determining whether a first threshold of voice activity is met based on the first probability of voice activity and the second probability of voice activity;

in accordance with a determination that the first threshold of voice activity is met, determining that a voice onset has occurred; and

in accordance with a determination that the first threshold of voice activity is not met, forgoing determining that a voice onset has occurred,

wherein:

the wearable head device comprises a frame,

the frame comprises a first left eye portion configured to rest at a first height with respect to a user's eye when the frame is worn by the user and a second right eye portion configured to rest at a second height with respect to the user's eye when the frame is worn by the user, the second height different from the first height,

the first microphone is disposed on the first left eye portion of the frame, and

the second microphone is disposed on the second right eye portion of the frame.

9. The method of claim 8 , wherein the first height is a positive height and the second height is a negative height.

10. The method of claim 9 , wherein the first height and the second height are equal in magnitude.

11. The method of claim 9 , wherein the first height and the second height are unequal in magnitude.

12. The method of claim 8 , wherein the first left eye portion comprises a first corner of the frame and the second right eye portion comprises a second corner of the frame.

13. The method of claim 8 , wherein the first microphone is configured to rest a first distance from a user's mouth, and wherein the second microphone is configured to rest a second distance from the user's mouth, the first distance unequal to the second distance.

14. The method of claim 8 , further comprising determining a time offset associated with a difference between the first distance and the second distance, wherein determining the second probability of voice activity based on the first voice audio signal and the second voice audio signal comprises compensating for the time offset.

15. A non-transitory computer-readable medium storing one or more instructions, which, when executed by one or more processors, cause the one or more processors to perform a method comprising:

receiving, via a first microphone of a wearable head device, a first voice audio signal;

determining a first probability of voice activity based on the first voice audio signal;

receiving, via a second microphone of the wearable head device, a second voice audio signal;

combining the first voice audio signal and the second voice audio signal to produce a third voice audio signal;

determining a second probability of voice activity based on the third voice audio signal;

determining whether a first threshold of voice activity is met based on the first probability of voice activity and the second probability of voice activity;

in accordance with a determination that the first threshold of voice activity is met, determining that a voice onset has occurred; and

in accordance with a determination that the first threshold of voice activity is not met, forgoing determining that a voice onset has occurred,

wherein:

the wearable head device comprises a frame,

the frame comprises a first left eye portion configured to rest at a first height with respect to a user's eye when the frame is worn by the user and a second right eye portion configured to rest at a second height with respect to the user's eye when the frame is worn by the user, the second height different from the first height,

the first microphone is disposed on the first left eye portion of the frame, and

the second microphone is disposed on the second right eye portion of the frame.

16. The non-transitory computer-readable medium of claim 15 , wherein the first height is a positive height and the second height is a negative height.

17. The non-transitory computer-readable medium of claim 16 , wherein the first height and the second height are equal in magnitude.

18. The non-transitory computer-readable medium of claim 16 , wherein the first height and the second height are unequal in magnitude.

19. The non-transitory computer-readable medium of claim 15 , wherein the first left eye portion comprises a first corner of the frame and the second right eye portion comprises a second corner of the frame.

20. The non-transitory computer-readable medium of claim 15 , wherein the first microphone is configured to rest a first distance from a user's mouth, and wherein the second microphone is configured to rest a second distance from the user's mouth, the first distance unequal to the second distance.