Systems and methods for identifying an active speaker in a virtual meeting

A system comprising a processor configured to:

• associate a user device of a participant of a virtual meeting with a physical location from which the participant and one or more additional participants participate in the virtual meeting;
• determine that the participant provides a user input via the user device during the virtual meeting, the user input indicating that the participant will speak and comprising at least one of a hand gesture input or a touch input;
• implementing, based on the participant providing the user input indicating that the participant will speak, a voice detection component to begin listening for an utterance from the participant;
• and
• provide, based on the user input and the associating and while the voice detection component listens for the utterance, an active speaker indicator for presentation in a virtual meeting interface provided to one or more participants of the virtual meeting, the active speaker indicator specifying a participant identifier representative of the participant and a place identifier representative of the physical location from which the participant participates in the virtual meeting,
• wherein the providing of the active speaker indicator includes:
• generating, based on the participant providing the user input indicating that the participant will speak, a graphical element including the participant identifier of the participant and a video-only stream of the participant captured by the user device;
• and
• providing the graphical element for presentation in the virtual meeting interface, the graphical element provided for presentation together with a video-and-audio stream of the physical location captured by an on-site conference system of the physical location, the video- and-audio stream including the participant and the one or more additional participants.

A non-transitory computer-readable medium storing instructions that, when executed, direct a processor of a virtual meeting management system to:

• associate a user device of a participant of a virtual meeting with a physical location from which the participant and one or more additional participants participate in the virtual meeting;
• determine that the participant provides a user input via the user device during the virtual meeting, the user input indicating that the participant will speak and comprising at least one of a hand gesture input or a touch input;
• implement, based on the participant providing the user input indicating that the participant will speak, a voice detection component to begin listening for an utterance from the participant;
• and
• provide, based on the user input and the associating and while the voice detection component listens for the utterance, an active speaker indicator for presentation in a virtual meeting interface provided to one or more participants of the virtual meeting, the active speaker indicator specifying a participant identifier representative of the participant and a place identifier representative of the physical location from which the participant participates in the virtual meeting,
• wherein the providing of the active speaker indicator includes:
• generating, based on the participant providing the user input indicating that the participant will speak, a graphical element including the participant identifier of the participant and a video-only stream of the participant captured by the user device;
• and
• providing the graphical element for presentation in the virtual meeting interface, the graphical element provided for presentation together with a video-and-audio stream of the physical location captured by an on-site conference system of the physical location, the video- and-audio stream including the participant and the one or more additional participants.