Automatic input device selection for media conferences

1. A method for audio signal selection, the method comprising:

initiating a media conference including a participant device comprising a plurality of input devices that when activated provide a plurality of input audio signals for a first participant of the media conference;

determining a first characteristic of a first input audio signal of the plurality of audio input signals for the first participant received from a first input device of the plurality of input devices;

determining that the first characteristic of the first input audio signal does not satisfy a threshold;

activating, based on determining that the first characteristic of the first input audio signal does not satisfy the threshold, a second input device of the plurality of input devices;

determining a second characteristic of a second input audio signal of the plurality of audio input signals for the first participant received from the second input device;

comparing, based on determining that the first characteristic of the first input audio signal does not satisfy the threshold, the first characteristic to the second characteristic;

determining, based on comparing the first characteristic to the second characteristic, that a quality of the second input audio signal is greater than a quality of the first input audio signal; and

selecting, from among the plurality of audio input signals for the first participant, based on the determining that the quality of the second input audio signal is greater than the quality of the first input audio signal, the second input audio signal for transmission to at least one other participant of the media conference.

2. The method of claim 1 , wherein:

the first characteristic of the first input audio signal is at least one of an amplitude, a signal-to-noise ratio, reverberation, an echo, a voice naturalness, or a muffle of the first input audio signal, and

the second characteristic of the second input audio signal is at least one of an amplitude, a signal-to-noise ratio, reverberation, an echo, a voice naturalness, or a muffle of the second input audio signal.

3. The method of claim 1 , further comprising:

determining that the second input audio signal is no longer being received; and

automatically changing, in response to determining that the second input audio signal is no longer being received, a selected input audio signal from the second input audio signal to the first input audio signal or a third input audio signal of the plurality of input audio signals.

4. The method of claim 1 , further comprising:

determining that a third input device is available to the participant device;

activating, in response to determining that the third input device is available, the third input device;

determining an updated second characteristic of the second input audio signal;

determining a third characteristic of a third input audio signal received from the third input audio signal;

comparing the second characteristic to the third characteristic;

determining, based on comparing the second characteristic to the third characteristic, that a quality of the third input audio signal is greater than a quality of the second input audio signal; and

automatically changing, based on determining that the quality of the third input audio signal is greater than the quality of the second input audio signal, a selected input audio signal from the second input audio signal to the third input audio signal.

5. The method of claim 1 , wherein the first input audio signal and the second input audio signal are captured simultaneously.

6. A media conferencing service comprising:

a computing node and a non-transitory computer-readable medium, the non-transitory computer-readable medium having stored therein computer-readable instructions that, upon execution by the computing node, configure the media conferencing service to perform operations comprising:

receiving, from a first input device of a plurality of input devices that when activated provide a plurality of input audio signals for a first participant of a media conference, a first input audio signal of the plurality of input audio signals for the first participant;

determining a first characteristic of the first input audio signal;

determining that the first characteristic of the first input audio signal does not satisfy a threshold;

activating, based on determining that the first characteristic of the first input audio signal does not satisfy the threshold, a second input device of the plurality of input devices;

determining a second input audio signal of the plurality of input audio signals for the first participant from the second input device;

determining a second characteristic of the second input audio signal;

comparing, based on determining that the first characteristic of the first input audio signal does not satisfy the threshold, the first characteristic to the second characteristic;

determining, based on comparing the first characteristic to the second characteristic, that a quality of the second input audio signal is greater than a quality of the first input audio signal; and

selecting, from among the plurality of audio input signals for the first participant, based on the determining that the quality of the second input audio signal is greater than the quality of the first input audio signal, the second input audio signal for transmission to at least one other participant of the media conference.

7. The media conferencing service of claim 6 , wherein the computer-readable instructions upon execution further configure the media conferencing service to:

initiate the media conference; and

select, in response to initiating the media conference, the first input audio signal.

8. The media conferencing service of claim 7 , wherein the computer-readable instructions upon execution configure the media conferencing service to select the second input audio signal by changing, following initiation of the media conference, the selection of the first input audio signal to the second input audio signal.

9. The media conferencing service of claim 6 , wherein:

the first characteristic of the first input audio signal is at least one of an amplitude, a signal-to-noise ratio, reverberation, an echo, a voice naturalness, or a muffle of the first input audio signal, and

the second characteristic of the second input audio signal is at least one of an amplitude, a signal-to-noise ratio, reverberation, an echo, a voice naturalness, or a muffle of the second input audio signal.

10. The media conferencing service of claim 6 , wherein the computer-readable instructions upon execution further configure the media conferencing service to:

determine that the second input audio signal is no longer being received; and

select, in response to determining that the second input audio signal is no longer being received, the first input audio signal or a third input audio signal.

11. The media conferencing service of claim 6 , wherein the computer-readable instructions upon execution further configure the media conferencing service to:

receive, from a user participating in the media conference, quality feedback indicating the quality of the first input audio signal; and

select, in response to receiving the quality feedback indicating that the quality of the first input audio signal, the second input device.

12. The media conferencing service of claim 6 , wherein the computer-readable instructions upon execution configure the media conferencing service to select the second input device by:

outputting, to a participant device, a notification indicating the second input device; and

receiving, from the participant device, acknowledgement of the notification.

13. The media conferencing service of claim 6 , wherein the computer-readable instructions upon execution configure the media conferencing service to select the second input audio signal automatically without human intervention.

14. The media conferencing service of claim 6 , wherein the computer-readable instructions upon execution configure the media conferencing service to determine that the quality of the second input audio signal is greater than the quality of the first input audio signal by applying machine learning to the first characteristic of the first input audio signal and the second characteristic of the second input audio signal.

15. The media conferencing service of claim 6 , wherein the first input audio signal and the second input audio signal are captured simultaneously.

16. A non-transitory computer-readable storage medium having stored thereon computer-readable instructions, the computer-readable instructions, upon execution on one or more computing devices, at least cause the one or more computing devices to:

receive, from a first input device of a plurality of input devices that when activated provide a plurality of input audio signals for a first participant of a media conference, a first input audio signal of the plurality of input audio signals;

determine a first characteristic of the first input audio signal;

determine that the first characteristic of the first input audio signal does not satisfy a threshold;

activate, based on determining that the first characteristic of the first input audio signal does not satisfy the threshold, a second input device of the plurality of input devices;

receive a second input audio signal of the plurality of input audio signals for the first participant from the second input device;

determine a second characteristic of the second input audio signal;

compare, based on determining that the first characteristic of the first input audio signal does not satisfy the threshold, the first characteristic to the second characteristic;

determine, based on comparing the first characteristic to the second characteristic, that a quality of the second input audio signal is greater than a quality of the first input audio signal; and

select, from among the plurality of audio input signals for the first participant, based on determining that the quality of the second input audio signal is greater than the quality of the first input audio signal, the second input audio signal for transmission to at least one other participant of the media conference.

17. The non-transitory computer-readable storage medium of claim 16 , wherein the computer-readable instructions, upon execution on the one or more computing devices, further cause the one or more computing devices to:

initiate the media conference including a participant device, wherein the first input device and the second input device are associated with the participant device; and

select, in response to initiating the media conference, the first input audio signal.

18. The non-transitory computer-readable storage medium of claim 17 , wherein the computer-readable instructions, upon execution on the one or more computing devices, cause the one or more computing devices to select the second input audio signal by changing a selection of the first input audio signal to the second input audio signal.

19. The non-transitory computer-readable storage medium of claim 16 , wherein the first input audio signal and the second input audio signal are audio signals, and wherein:

the first characteristic of the first input audio signal is at least one of an amplitude, a signal-to-noise ratio, reverberation, an echo, a voice naturalness, or a muffle of the first input audio signal, and

the second characteristic of the second input audio signal is at least one of an amplitude, a signal-to-noise ratio, reverberation, an echo, a voice naturalness, or a muffle of the second input audio signal.

20. The non-transitory computer-readable storage medium of claim 16 , wherein the first input audio signal and the second input audio signal are captured simultaneously.