Smart audio muting in a videoconferencing system
A smart muting method for a teleconference or videoconference participant includes detecting audio of an audio-video stream; analyzing video data of the audio-video stream with respect to the detected audio; determining that the audio corresponds to an intended communication, based on the analyzing video data of the audio-video stream with respect to the detected audio; and rendering the audio, responsive to determining that the audio corresponds to an intended communication.
1. A smart muting method, comprising:
detecting, using a processor, audio of an audio-video stream;
analyzing, using the processor, video data of the audio-video stream with respect to the detected audio;
determining, using the processor, that the audio corresponds to an intended communication, based on the analyzing video data of the audio-video stream with respect to the detected audio; and
rendering, using the processor, the audio, responsive to determining that the audio corresponds to an intended communication,
wherein analyzing video data of the audio-video stream with respect to the detected audio comprises determining a first set of text corresponding to lip movements.
2. The method of claim 1 , wherein detecting audio of the audio-video stream comprises buffering the audio of the audio-video stream.
3. The method of claim 2 , wherein rendering the audio, responsive to determining that the audio corresponds to an intended communication comprises transmitting the buffered audio of the audio-video stream to a remote endpoint.
4. The method of claim 1 , wherein analyzing video data of the audio-video stream with respect to the detected audio further comprises determining a second set of text corresponding to the audio of the audio-video stream.
5. The method of claim 4 , wherein determining that the audio corresponds to an intended communication comprises determining that a degree to which the first set of text and the second set of text correspond exceeds a predetermined threshold.
6. The method of claim 5 , wherein the predetermined threshold corresponds to a degree of seventy-five percent.
7. A teleconferencing system, comprising:
a processor configured to:
detect audio of an audio-video stream;
analyze video data of the audio-video stream with respect to the detected audio;
determine that the audio corresponds to an intended communication, based on the analyzing video data of the audio-video stream with respect to the detected audio;
and render the audio, responsive to determining that the audio corresponds to an intended communication,
wherein analyzing video data of the audio-video stream with respect to the detected audio comprises determining a first set of text corresponding to lip movements.
8. The teleconferencing system of claim 7 , wherein the processor is further configured to detect audio of the audio-video stream by buffering the audio of the audio-video stream.
9. The teleconferencing system of claim 8 , wherein the processor is further configured to render the audio, responsive to determining that the audio corresponds to an intended communication by transmitting the buffered audio of the audio-video stream to a remote endpoint.
10. The teleconferencing system of claim 7 , wherein the processor is further configured to analyze video data of the audio-video stream with respect to the detected audio by determining a second set of text corresponding the audio of the audio-video stream.
11. The teleconferencing system of claim 10 , wherein the processor is further configured to determine that the audio corresponds to an intended communication by determining that a degree to which the first set of text and the second set of text correspond exceeds a predetermined threshold.
12. The teleconferencing system of claim 11 , wherein the predetermined threshold corresponds to a degree of seventy-five percent.
13. A non-transitory computer readable memory storing instructions executable by a processor, wherein the instructions comprise instructions to:
detect audio of an audio-video stream;
analyze video data of the audio-video stream with respect to the detected audio;
determine that the audio corresponds to an intended communication, based on the analyzing video data of the audio-video stream with respect to the detected audio; and
render the audio, responsive to determining that the audio corresponds to an intended communication,
wherein the instructions to analyze video data of the audio-video stream with respect to the detected audio comprise instructions to determine a first set of text corresponding to lip movements.
14. The memory of claim 13 , wherein the instructions to detect audio of the audio-video stream comprise instructions to buffer the audio of the audio-video stream.
15. The memory of claim 14 , wherein the instructions to render the audio, responsive to determining that the audio corresponds to an intended communication comprise instructions to transmit the buffered audio of the audio-video stream to a remote endpoint.
16. The memory of claim 13 , wherein the instructions to analyze video data of the audio-video stream with respect to the detected audio comprise instructions to determine a second set of text corresponding to the audio of the audio-video stream.
17. The memory of claim 16 , wherein the instructions to determine that the audio corresponds to an intended communication comprise instructions to determine that a degree to which the first set of text and the second set of text correspond exceeds a confidence value established responsive detection of one or more user selections.