All research

Active speaker detection on split screens: specialists near chance

Result

AVA-trained detectors (TalkNet, LR-ASD, Light-ASD, LRX-ASD) pick the right half 55-60% of the time, against 50% chance. Gemini 4 Argon gets 94.8%, and 7 of 7 when the same person is on both sides.

Data
116 pairs
Compute
1x H100 80GB
Chance
50%
Metric
Pairs right %

Reframing a 16:9 news shot for a 9:16 phone means choosing which face to keep, and the obvious choice is the person talking. Active speaker detectors do exactly that, and the well-known ones score 92–95% mAP on the AVA-ActiveSpeaker benchmark. So we built the case news actually throws at them: a split screen with two people, both moving their lips, and one voice. The detectors pick the right person 55–60% of the time. A coin gets 50%.

Read the full study on Every Local AI