Your question is Active Speaker Detection Changes. Take a moment with it on the right.
Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).
Describe how you would detect changes in active speaker status in an audio stream.
Assume you must process short audio frames online and distinguish speech from silence or background noise. Explain the features, model, temporal smoothing, change-point logic, evaluation metrics, and latency tradeoffs you would use.