Weighted Top-K Audio Detector Training (Late-fusion)

Booting…
idle

Training

Source

Model

Pick an existing model or choose “New…” to create one. Train (mic/file/folder/sender), then click “Recompute Weights”.

Quiet calibration

Calibrate thresholds
Duration
20s
Thresholds
OFF 0.25
ON 0.35
Keep the room quiet. (Uses the selected source: Mic or Sender.)

Live audio detection

Detection
Uses the active model & thresholds and the selected source (Mic or Sender).

Weights

Live dynamic weights (unsaved preview)

Top-K normalized weights recomputed on every training inference. Not stored.

Active model weights (Top-K, normalized)

What detection uses (until you click “Recompute Weights”).

Fused score over time

fused (raw) fused (EMA) thresh ON thresh OFF

Logs