Speech Emotion Recognition on CASE Zero-Shot v1 (test)
59.38Accuracy (ACC)FAS
Evaluation results
| Method | Links | ||
|---|---|---|---|
| FASSemantic Modality=true, Acoustic Modality=true2026.01 | 59.38 | 55.08 | |
| WhisperSemantic Modality=true, Acoustic Modality=false2026.01 | 47.26 | 44.97 | |
| Qwen2.5-OmniSemantic Modality=true, Acoustic Modality=false2026.01 | 34.66 | 30.21 | |
| CLAPSemantic Modality=true, Acoustic Modality=false2026.01 | 34.46 | 31.93 | |
| WavLMSemantic Modality=true, Acoustic Modality=true2026.01 | 34.2 | 33.92 | |
| HuBERTSemantic Modality=true, Acoustic Modality=true2026.01 | 32.9 | 32.24 | |
| Qwen2-AudioSemantic Modality=true, Acoustic Modality=false2026.01 | 32.53 | 27.08 | |
| Emotion2VecSemantic Modality=false, Acoustic Modality=false2026.01 | 31.48 | 28.42 | |
| VibevoiceSemantic Modality=false, Acoustic Modality=true2026.01 | 30.03 | 25.9 | |
| MingTok-AudioSemantic Modality=false, Acoustic Modality=true2026.01 | 29.24 | 25.61 | |
| wav2vec 2.0Semantic Modality=true, Acoustic Modality=true2026.01 | 25.59 | 22.83 | |
| EnCodecSemantic Modality=false, Acoustic Modality=true2026.01 | 24.54 | 18.81 |