System and method for identifying active communicator
A method includes receiving a plurality of video data associated with a plurality of users in an electronic conference. The method further includes processing the plurality of video data to determine whether an action of a user matches an active communicator action. In response to determining that the action of the user matches the active communicator action, the method further includes determining that the user intends to actively communicate audio or video data in the electronic conference. Moreover, the method includes identifying the user as an active communicator within the electronic conference.
1. A web-based server for determining an active user, comprising:
a memory storing a set of instructions; and
at least one processor configured to execute the instructions to:
facilitate an electronic conference between a plurality of users;
receive a plurality of video data associated with the plurality of users in the electronic conference;
process the plurality of video data, using a machine learning model, to determine whether an action of a user matches an active communicator action, wherein the active communicator action is at least one of pointing to a display, staring at a predetermined graphical user interface (GUI) icon for a predetermined amount of time;
in response to determining that the action of the user matches the active communicator action, identify the user as an active communicator within the electronic conference by graphically designating the identified user as an active communicator within a GUI.
2. The web-based server as described in claim 1 , wherein the identified user is distinguished from users that are inactive communicators of the electronic conference.
3. The web-based server as described in claim 1 , wherein the graphical designation is by enlarging a participant frame associated with the identified user in comparison to the users that are inactive communicators, by inserting a colored border around the participant frame associated with the identified user in comparison to the users that are inactive communicators, or by inserting an indicator icon in the participant frame associated with the identified user.
4. The web-based server as described in claim 1 , wherein the processor is configured to accentuate an audio data or a video data of the identified user in comparison to users that are inactive communicators.
5. The web-based server as described in claim 1 , wherein the processor is further configured to suppress audio data for a subset of users other than the identified user.
6. The web-based server as described in claim 1 , wherein the user is identified as the active communicator based on video data and independent from audio data.
7. A method, comprising:
receiving a plurality of video data associated with a plurality of users in an electronic conference;
processing the plurality of video data, using a machine learning model, to determine whether an action of a user matches an active communicator action, wherein the active communicator action is at least one of raising a hand, pointing to a display, nodding, staring at a predetermined graphical user interface (GUI) icon for a predetermined amount of time, clapping;
in response to determining that the action of the user matches the active communicator action, determining that the user intends to actively communicate audio or video data in the electronic conference; and
identifying the user as an active communicator within the electronic conference, wherein the processor is configured to accentuate an audio data and a video data of the identified user in comparison to users that are inactive communicators.
8. The method as described in claim 7 , further comprising:
rendering a graphical user interface (GUI) associated with the electronic conference, wherein the GUI includes participant frame associated with each user of the plurality of users.
9. The method as described in claim 8 , further comprising:
designating graphically the identified user as the active communicator within the GUI.
10. The method as described in claim 9 , wherein the designating graphically distinguishes the identified user from users that are inactive communicators of the electronic conference.
11. The method as described in claim 10 , wherein the identified user is graphically distinguished from the users that are inactive communicators of the electronic conference by enlarging a participant frame associated with the identified user in comparison to the users that are inactive communicators, by inserting a colored border around to the participant frame associated with the identified user in comparison to the users that are inactive communicators, or by inserting an indicator icon in the participant frame associated with the identified user.
12. The method as described in claim 7 , wherein an audio data or the video data of the identified user is accentuated in comparison to users that are inactive communicators.
13. The method as described in claim 7 , wherein the active communicator action is a sign language.
14. The method as described in claim 7 , further comprising:
suppressing audio data for a subset of users other than the identified user.
15. The method as described in claim 7 , wherein the identifying is independent of receiving an audio data.
16. A non-transitory computer-readable medium storing a set of instructions that, when executed by a processor, cause: facilitating an electronic conference between a plurality of users; receiving a plurality of video data associated with the plurality of users in the electronic conference; processing the plurality of video data, using a machine learning model, to determine whether an action of a user matches an active communicator action, wherein the active communicator action is staring at a predetermined graphical user interface (GUI) icon for a predetermined amount of time; in response to determining that the action of the user matches the active communicator action, identifying the user as an active communicator within the electronic conference by graphically designating the identified user as an active communicator within a GUI.
17. The non-transitory computer-readable medium as described in claim 16 , wherein the identified user is distinguished from users that are inactive communicators of the electronic conference.
18. The non-transitory computer-readable medium as described in claim 16 , wherein the graphical designating include enlarging a participant frame associated with the identified user in comparison to the users that are inactive communicators, inserting a colored border around the participant frame associated with the identified user in comparison to the users that are inactive communicators, or inserting an indicator icon in the participant frame associated with the identified user.
19. The non-transitory computer-readable medium as described in claim 16 , wherein an audio data or a video data of the identified user is accentuated in comparison to users that are inactive communicators.
20. The non-transitory computer-readable medium as described in claim 16 , wherein audio data for a subset of users other than the identified user is suppressed.
21. The non-transitory computer-readable medium as described in claim 16 , wherein the user is identified as the active communicator based on video data and independent from audio data.