Speech Emotion Recognition on CAFE
52Macro F1B-GRPO
Evaluation results
| Method | Links | |
|---|---|---|
| B-GRPOTraining Protocol=RL-based unsupervised (after 100 epoch supervised pre-training)2026.02 | 52 | |
| DINOTraining Protocol=Unsupervised learning2026.02 | 51 | |
| Full labeledTraining Protocol=Supervised (full dataset)2026.02 | 50.3 | |
| Same epochsTraining Protocol=Supervised (200 epochs)2026.02 | 48.7 | |
| BaselineTraining Protocol=Supervised (half labeled, 100 epochs)2026.02 | 44.7 |