Speech Emotion Recognition on MESD Spanish (test)
87.79Weighted AccuracyPhysioSER
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| PhysioSERBackbone=BEATs2026.02 | 87.79 | 88.01 | 87.74 | |
| BEATsConfiguration=Backbone-only2026.02 | 74.42 | 73.97 | 73.66 | |
| PhysioSERBackbone=WavLM2026.02 | 72.09 | 71.73 | 71.36 | |
| PhysioSERBackbone=Emotion2Vec2026.02 | 70.35 | 70.48 | 69.42 | |
| PhysioSERBackbone=CLAP2026.02 | 67.44 | 68.41 | 67.21 | |
| CLAPConfiguration=Backbone-only2026.02 | 65.7 | 64.15 | 63.78 | |
| Emotion2VecConfiguration=Backbone-only2026.02 | 63.95 | 63.19 | 62.81 | |
| PhysioSERBackbone=HuBERT2026.02 | 63.37 | 63.82 | 63.51 | |
| PhysioSERBackbone=Wav2vec22026.02 | 62.21 | 61.97 | 61.83 | |
| WavLMConfiguration=Backbone-only2026.02 | 52.91 | 51.2 | 51.16 | |
| HuBERTConfiguration=Backbone-only2026.02 | 46.51 | 44.3 | 43.94 | |
| Wav2vec2Configuration=Backbone-only2026.02 | 34.88 | 33.66 | 33.34 |