Speech Emotion Recognition on CASIA (Macro F1)
57.2Macro F1Full labeled
Evaluation Results
| Method | Links | |
|---|---|---|
| Full labeledTraining Protocol=Supervised (full dataset)2026.02 | 57.2 | |
| B-GRPOTraining Protocol=RL-based unsupervised (after 100 epoch supervised pre-training)2026.02 | 37 | |
| Same epochsTraining Protocol=Supervised (200 epochs)2026.02 | 29.5 | |
| DINOTraining Protocol=Unsupervised learning2026.02 | 28.5 | |
| BaselineTraining Protocol=Supervised (half labeled, 100 epochs)2026.02 | 25 |