Gestures for switching audio endpoints

1 . A system, comprising:

an image sensor;

a plurality of audio endpoints, the plurality of audio endpoints including a plurality of audio output endpoints and a plurality of audio input endpoints; and

an electronic device comprising a controller, wherein the controller is to:

receive images of a user's face from the image sensor;

detect, in the images, a gesture of the user to point to a feature on the user's face; and

transition between use of the plurality of audio output endpoints and between use of the plurality of audio input endpoints in response to detecting the gesture of the user simultaneously pointing to a first feature and a second feature on the user's face such that one of the plurality of audio endpoints is activated and another of the plurality of audio endpoints is deactivated.

2 . The system of claim 1 , wherein the plurality of audio output endpoints comprises an onboard speaker of the electronic device and an external speaker coupled to the electronic device.

3 . The system of claim 2 , wherein the plurality of audio input endpoints comprises an onboard microphone and an external microphone coupled to the electronic device.

4 . The system of claim 1 , wherein the controller is to detect the gesture in the images using a neural network.

5 . The system of claim 1 , wherein the controller is further to provide an indication to the user after the transition in response to detecting the gesture.

6 . The system of claim 1 , wherein the controller is further to detect, in the images, the feature on the user's face using a machine-learning model.

7 . The system of claim 1 , wherein the one of the plurality of audio endpoints that is activated is an external audio endpoint, external from the electronic device, and the another of the plurality of audio endpoints that is deactivated is an onboard audio endpoint, integrated with the electronic device.

8 . A non-transitory machine-readable medium storing instructions, which, when executed by a processor of an electronic device, cause the processor to:

detect a first feature of a user's face and a second feature of the user's face in images captured by an image sensor coupled to the electronic device;

detect, in the images, a gesture of the user to indicate the first feature;

select, among a plurality of audio endpoints coupled to the electronic device, a first audio output endpoint for activation and use in response to detecting the gesture to indicate the first feature;

detect, in the images, a gesture of the user to indicate the second feature; and

select an audio input endpoint for use in response to detecting the gesture to indicate the second feature.

9 . The non-transitory machine-readable medium of claim 8 , wherein the electronic device is coupled to a second audio output endpoint among the plurality of audio endpoints, and

wherein the instructions, when executed by the processor, cause the processor to switch to the first audio output endpoint from the second audio output endpoint in response to detecting the gesture.

10 . The non-transitory machine-readable medium of claim 9 , wherein the instructions, when executed by the processor, cause the processor to:

detect, in the images, the gesture after switching to the first audio output endpoint; and, in response,

switch from the first audio output endpoint to the second audio output endpoint.

11 . The non-transitory, machine-readable medium of claim 8 , wherein the first feature comprises an ear, and the second feature comprises a mouth.

12 . The non-transitory machine-readable medium of claim 8 , wherein the instructions, when executed by the processor, further cause the processor to provide an indication to the user upon selecting the first audio endpoint for use in response to detecting the gesture.

13 . An electronic device, comprising:

a housing;

an image sensor;

an onboard audio endpoint that is integrated with the housing;

a communication assembly to communicatively couple with an external audio endpoint that is separate from the housing; and

a controller positioned within the housing, wherein the controller is to:

detect a first facial feature of a user using the image sensor;

detect a first gesture of the user using the image sensor, in which the user points to the first facial feature; and

switch between use of the onboard audio endpoint and the external audio endpoint, via the communication assembly, in response to detecting the first gesture.

14 . The electronic device of claim 13 , comprising:

a second onboard audio endpoint that is integrated with the housing; and

a second external audio endpoint that is to be communicatively coupled to the communication assembly,

wherein the controller is to:

detect a second facial feature of the user using the image sensor; and

detect a second gesture of the user using the image sensor, in which the user points to the second facial feature; and

switch between use of the second onboard audio endpoint and the second external audio endpoint, via the communication assembly, in response to detecting the second gesture.

15 . The electronic device of claim 14 , wherein the controller is to:

detect both the first gesture and the second gesture simultaneously; and

switch between use of the onboard audio endpoint and the external audio endpoint and between use of the second onboard audio endpoint and the second external audio endpoint in response to detecting the first gesture and the second gesture simultaneously.

16 . The electronic device of claim 13 , wherein the controller is to detect the first facial feature and the first gesture using a neural network.

17 . The electronic device of claim 13 , wherein the onboard audio endpoint comprises an onboard speaker and the external audio endpoint comprises a speaker on a headset.