Systems and methods for audience interactions in real-time multimedia applications

A method for a real-time video conference, comprising:

• acquiring, via one or more input devices of a broadcast computing system, video and audio of a user of the broadcast computing system;
• transmitting, to a plurality of remote computing systems including a remote computing system via one or more media servers over a network, the video and/or the audio of the user, wherein the one or more media servers selectively forward or mix media streams between the plurality of remote computing systems along with the video and/or the audio of the user;
• receiving, from the remote computing system via the one or more media servers and a data event channel over the network, a media stream acquired at the remote computing system and an event detection message indicating an event automatically detected with a machine learning model at the remote computing system in the media stream;
• and
• automatically outputting, via an output device of the broadcast computing system, the media stream based on the event detection message.

A system for a real-time video conference, comprising:

• one or more media servers;
• a broadcast computing system communicatively coupled to the one or more media servers via a network and configured to publish a broadcast media stream;
• and
• a plurality of client computing systems including at least a first client computing system and a second client computing system communicatively coupled to the one or more media servers via the network and configured to acquire a first media stream and a second media stream, respectively, wherein the one or more media servers transmit the broadcast media stream from the broadcast computing system to the plurality of client computing systems, the first media stream from the first client computing system to the second client computing system, and the second media stream from the second client computing system to the first client computing system;
• wherein the first client computing system is configured with executable instructions in non-transitory memory that when executed cause a processor of the first client computing system to:
• automatically detect, with a machine learning model, an event in the first media stream, the first media stream comprising audio and/or video of a user of the first client computing system;
• and
• transmit, to the one or more media servers and/or a data event channel over the network, an event detection message indicating the event;
• wherein the broadcast computing system is configured with executable instructions in non-transitory memory that when executed cause a processor of the broadcast computing system to:
• receive, from the first computing system one or more media servers and/or the data event channel over the network, the event detection message;
• and
• control an output device of the broadcast computing system to indicate the event to a user of the broadcast computing system responsive to receiving the event detection message.