Scripted vs spontaneous speech detection on External interview-domain dataset
95.8AccuracySEAM
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SEAMSeed=1339, Backbone=DistilHuBERT, Window size=8 s, Layer unfreezing=top-1-layer, Training epochs=32026.06 | 95.8 | 0.9745 | |
| SEAMSeed=1337, Backbone=DistilHuBERT, Window size=8 s, Layer unfreezing=top-1-layer, Training epochs=32026.06 | 95.4 | 0.9725 | |
| SEAMSeed=Mean, Backbone=DistilHuBERT, Window size=8 s, Layer unfreezing=top-1-layer, Training epochs=32026.06 | 95.17 | 0.9713 | |
| SEAMSeed=1338, Backbone=DistilHuBERT, Window size=8 s, Layer unfreezing=top-1-layer, Training epochs=32026.06 | 94.31 | 0.9669 |