Scripted vs spontaneous speech detection on Internal curated English dataset (test)
96.81AccuracySEAM
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SEAMSeed=1339, Backbone=DistilHuBERT, Window size=8 s, Layer unfreezing=top-1-layer, Training epochs=32026.06 | 96.81 | 98.02 | |
| SEAMSeed=1337, Backbone=DistilHuBERT, Window size=8 s, Layer unfreezing=top-1-layer, Training epochs=32026.06 | 96.39 | 97.81 | |
| SEAMSeed=Mean, Backbone=DistilHuBERT, Window size=8 s, Layer unfreezing=top-1-layer, Training epochs=32026.06 | 96.23 | 97.66 | |
| SEAMSeed=1338, Backbone=DistilHuBERT, Window size=8 s, Layer unfreezing=top-1-layer, Training epochs=32026.06 | 95.48 | 97.15 |