Determining prioritized participants during a video conference
A system may receive, during a video conference, video feeds corresponding to conference participants. The system may determine a prioritized participant from the conference participants by using a machine learning model and historical conference participant information. In some implementations, the system may receive input from a conference participant that causes the conference participant to be a prioritized participant (e.g., the conference participant may self-select). The system may emphasize, in a graphical user interface (GUI) during the video conference, the video feed corresponding to the prioritized participant. In some implementations, determining the prioritized participant may include accessing a record including the historical conference participant information. The record may indicate that the prioritized participant and a participant using the GUI have a connection in an organization. In some implementations, the record may indicate that the prioritized participant used sign language during another video conference.
1 . A method, comprising:
receiving, during a video conference, video feeds corresponding to conference participants;
determining, by a machine learning model trained on historical conference participant information, a prioritized participant that is hard of hearing from the conference participants wherein the machine learning model is configured to perform operations including:
accessing records indicating prior use of sign language, team membership, or organizational relationships; and
detecting, in real-time, gestures associated with sign language in a video feed via software-based image processing; and
highlighting, in a graphical user interface (GUI) during the video conference, a video tile of the video feeds corresponding to the prioritized participant to enable the prioritized participant to communicate with other conference participants.
2 . The method of claim 1 , wherein the determining the prioritized participant from the conference participants using the machine learning model comprises:
accessing a record including the historical conference participant information, the record indicating that the prioritized participant and a participant using the GUI have a connection in an organization.
3 . The method of claim 1 , wherein the determining the prioritized participant from the conference participants using the machine learning model comprises:
accessing a record including the historical conference participant information, the record indicating that the prioritized participant used sign language during another video conference.
4 . The method of claim 1 , wherein the determining the prioritized participant from the conference participants using the machine learning model comprises:
determining that the prioritized participant is using sign language during the video conference.
5 . The method of claim 1 , further comprising:
training the machine learning model to detect a gesture associated with sign language in a video feed via software-based image or audio analysis and processing.
6 . The method of claim 1 , wherein emphasizing the video feed includes highlighting a participant tile associated with the video feed in the GUI.
7 . The method of claim 1 , further comprising:
determining multiple prioritized participants from the conference participants and emphasizing the video feeds corresponding to the multiple prioritized participants.
8 . The method of claim 1 , further comprising:
applying a filter that prevents a first conference participant from being the prioritized participant.
9 . The method of claim 1 , further comprising:
limiting a number of video feeds corresponding to conference participants that are displayed in the GUI.
10 . An apparatus, comprising:
a memory; and
a processor configured to execute instructions stored in the memory to:
receive, during a video conference, video feeds corresponding to conference participants;
determine, using a machine learning model trained on historical conference participant information, a prioritized participant that is hard of hearing from the conference participants wherein the machine learning model is configured to:
access records indicating prior use of sign language, team membership, or organizational relationships; and
detect, in real-time, gestures associated with sign language in a video feed via software-based image processing; and
highlight, in a graphical user interface (GUI) during the video conference, a video tile of the video feeds corresponding to the prioritized participant to enable the prioritized participant to communicate with other conference participants.
11 . The apparatus of claim 10 , wherein the historical conference participant information indicates that the prioritized participant and a participant using the GUI are members of a same team in an organization.
12 . The apparatus of claim 10 , wherein the machine learning model uses the historical conference participant information to predict that the prioritized participant is a user of sign language.
13 . The apparatus of claim 10 , wherein emphasizing the video feed includes increasing a size of a participant tile associated with the video feed in the GUI.
14 . The apparatus of claim 10 , wherein the processor is further configured to execute instructions stored in the memory to:
determine multiple prioritized participants from the conference participants as active speakers; and
emphasize the video feeds corresponding to the multiple prioritized participants as active speakers without displaying the other conference participants.
15 . The apparatus of claim 10 , wherein the processor is further configured to execute instructions stored in the memory to:
reduce a number of conference participants displayed in the GUI.
16 . A non-transitory computer readable medium storing instructions operable to cause one or more processors to perform operations comprising:
receiving, during a video conference, video feeds corresponding to conference participants;
determining, by a machine learning model trained on historical conference participant information, a prioritized participant that is hard of hearing from the conference participants wherein the machine learning model is configured to perform operations including:
accessing records indicating prior use of sign language, team membershit, or organizational relationships; and
detecting, in real-time, gestures associated with sign language in a video feed via software-based image processing; and
highlighting, in a graphical user interface (GUI) during the video conference, a video tile of the video feeds corresponding to the prioritized participant to enable the prioritized participant to communicate with other conference participants.
17 . The non-transitory computer readable medium storing instructions of claim 16 , wherein the historical conference participant information indicates that the prioritized participant and a participant using the GUI have a student/teacher or supervisor/subordinate relationship.
18 . The non-transitory computer readable medium storing instructions of claim 16 , wherein emphasizing the video feed includes changing a color in a background border of a participant tile associated with the video feed in the GUI.
19 . The non-transitory computer readable medium storing instructions of claim 16 , wherein the operations further comprise:
determining at least two prioritized participants from the conference participants and emphasizing the video feeds corresponding to the at least two prioritized participants without emphasizing the video feeds of other conference participants.
20 . The non-transitory computer readable medium storing instructions of claim 16 , wherein emphasizing the video feed includes ordering a participant tile associated with the video feed above another participant tile in the GUI.