Concurrent speaker highlighting in conferences

A device, comprising:

• one or more memories;
• and
• one or more processors, the one or more processors configured to execute instructions stored in the one or more memories to:
• maintain, for each of a plurality of conference participants of a conference, a respective speaker score based on speech activity in a respective audio data stream of each conference participant, wherein the speaker score is incremented in response to speech segments detected in the respective audio data stream and decremented in response to silence segments detected in the respective audio data stream;
• determine that a first audio data stream associated with a first conference participant of the conference meets predefined criteria, wherein the predefined criteria comprises the respective speaker score of the first conference participant exceeding a threshold;
• in response to determining that the first audio data stream meets the predefined criteria, add a first representation of the first conference participant to a stage area of a user interface associated with the conference, wherein the user interface includes the stage area and a gallery area;
• determine that a second audio data stream associated with a second conference participant of the conference meets the predefined criteria, wherein the predefined criteria comprises the respective speaker score of the second conference participant exceeding the threshold;
• and
• in response to determining that the second audio data stream meets the predefined criteria, add a second representation of the second conference participant to the stage area such that the stage area concurrently includes the first representation and the second representation.

A non-transitory computer-readable storage medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising:

• maintaining, for each of a plurality of conference participants of a conference, a respective speaker score based on speech activity in a respective audio data stream of each conference participant, wherein the speaker score is incremented in response to speech segments detected in the respective audio data stream and decremented in response to silence segments detected in the respective audio data stream;
• determining that a first audio data stream associated with a first conference participant of the conference meets predefined criteria, wherein the predefined criteria comprises the respective speaker score of the first conference participant exceeding a threshold;
• in response to determining that the first audio data stream meets the predefined criteria, adding a first representation of the first conference participant to a stage area of a user interface associated with the conference, wherein the user interface includes the stage area and a gallery area;
• determining that a second audio data stream associated with a second conference participant of the conference meets the predefined criteria, wherein the predefined criteria comprises the respective speaker score of the second conference participant exceeding the threshold;
• and
• in response to determining that the second audio data stream meets the predefined criteria, adding a second representation of the second conference participant to the stage area such that the stage area concurrently includes the first representation and the second representation.