Managing call sessions in multi-display systems

1. A client device comprising:

a first housing foldably attached to a second housing via a hinge;

a first display device positioned at a first surface of the first housing and a second display device positioned at a second surface of the first housing;

a sensor system including one or more sensors; and

one or more modules implemented at least in part in hardware of the client device to:

determine that a call session is to be output via the client device;

cause the call session to be output via the first display device based on detecting that a user is positioned to view the first display device;

receive sensor data from the sensor system indicating that a position of the user changes such that the user is positioned to view the second display device; and

cause, based on the change in the position of the user, the call session to be output on the second display device and audio input of the call session to be captured by an audio sensor on the second surface of the first housing.

2. The client device as described in claim 1 , wherein the sensor data further comprises an indication that the client device is in an open position based on a position of the first housing relative to the second housing, and wherein to cause the call session to be output via the first display device is further based on the indication that the client device is in the open position.

3. The client device as described in claim 1 , wherein the one or more modules are further implemented to output the call session via a first audio device based on detecting that the user is positioned to view the first display device, and to switch output of the call session to a second audio device based on the change in the position of the user.

4. The client device as described in claim 1 , wherein the one or more modules are further implemented to stop output of the call session via the first display device based on the change in the position of the user.

5. The client device as described in claim 1 , wherein the sensor data comprises audio data indicating that speech content from the user is detected at the second surface of the first housing of the client device.

6. The client device as described in claim 1 , wherein the one or more modules are further implemented to:

cause audio input for the call session to be captured from the first surface of the first housing based on detecting speech audio at the first surface;

determine that further speech audio is detected at the second surface of the first housing; and

cause further audio input for the call session to be captured from the second surface of the first housing based on detecting the further speech audio at the second surface.

7. The client device as described in claim 6 , wherein the one or more modules are further implemented to:

detect, while the call session is output on the second display device, speech audio at the first surface of the first housing; and

cause audio input for the call session to be captured at the first surface of the first housing.

8. The client device as described in claim 1 , wherein the detecting that the user is positioned to view the first display device is based at least in part on detecting the user within a field of view of a first camera positioned at the first surface of the first housing of the client device, and wherein the one or more modules are further implemented to:

detect that the user moves out of the field of view of the first camera; and

notify a second camera positioned at the second surface of the first housing to scan for an image of the user.

9. A client device comprising:

a first housing foldably attached to a second housing via a hinge;

a first display device and a first audio sensor positioned at a first surface of the first housing, and a second display device and a second audio sensor positioned at a second surface of the first housing;

a sensor system including one or more sensors; and

one or more modules implemented at least in part in hardware of the client device to:

determine that a call session is to be implemented via the client device;

cause audio input for the call session to be captured via the first audio sensor at the first surface of the first housing based on detecting speech audio at the first surface;

detect a change in an audio state that indicates further speech audio is detected at the second audio sensor at the second surface of the first housing;

cause further audio input for the call session to be captured via the second audio sensor at the second surface of the first housing based on the detected change in audio state; and

configure the further audio input as active audio for the call session based on detecting the further speech audio at the second audio sensor including to prioritize the further audio input over audio input received at the first audio sensor.

10. The client device of claim 9 , wherein the one or more modules are further implemented to cause audio input for the call session to be captured from the first surface based on determining that a user is positioned within a field of view of a camera positioned at the first surface of the first housing.

11. The client device of claim 9 , wherein the one or more modules are further implemented to:

cause visual content of the call session to be output via the first display device based on detecting the speech audio at the first audio sensor; and

cause the visual content of the call session to be output via the second display device based on detecting the further speech audio at the second audio sensor.

12. The client device of claim 9 , wherein the one or more modules are further implemented to:

cause visual content of the call session to be output via the first display device based on detecting a first user within a field of view of a first camera positioned at the first surface of the first housing; and

cause, while the visual content of the call session is output via the first display device, the visual content of the call session to be output via the second display device based on detecting a second user within a field of view of a second camera positioned at the second surface of the first housing.

13. The client device of claim 12 , wherein the one or more modules are further implemented to detect that the further speech audio originates from the second user.

14. The client device of claim 9 , wherein the one or more modules are further implemented to prioritize the further audio input by performing audio beamforming to focus on a source location of the further speech audio.

15. A method, comprising:

determining that a call session is to be output via a client device;

causing the call session to be output via a first display device and causing audio input for the call session to be captured via a first audio sensor of the client device based on detecting that a user is positioned to view the first display device;

receiving sensor data from a sensor system indicating that a position of a user changes such that the user is positioned to view a second display device; and

causing, based on the change in the position of the user, the call session to be output on the second display device and the audio input for the call session to be captured via a second audio sensor of the client device.

16. The method as described in claim 15 , wherein the client device comprises a first housing attached to a second housing via a hinge, the first display device is positioned at a first surface of the first housing, the second display device is positioned at a second surface of the first housing, and wherein the method further comprises monitoring a position of the user relative to the first display device based at least in part on:

determining that the client device is in an open position based on a position of the first housing relative to the second housing; and

determining that the call session is to be output via the client device.

17. The method as described in claim 15 , wherein detecting that the user is positioned to view the first display device is based on detecting the user within a field of view of a first camera of the client device, and wherein the sensor data indicating that the position of the user changes such that the user is positioned to view a second display device of the client device comprises detecting the user with a field of view of a second camera of the client device.

18. The method as described in claim 17 , further comprising:

detecting that the user moves out of the field of view of the first camera; and

notifying the second camera to scan for the user within the field of view of the second camera.

19. The method as described in claim 15 , further comprising:

detecting, while the user is positioned to view the second display device, that a different user is positioned to view the first display device; and

causing, based on detecting that the different user is positioned to view the first display device, the call session to be output via the first display device and the second display device.

20. The method as described in claim 15 , further comprising stopping output of the call session via the first display device based on the change in the position of the user.