Speech Emotion Recognition on EMOVO Zero-Shot v1 (test)
43.07AccuracyWhisper
Evaluation results
| Method | Links | ||
|---|---|---|---|
| WhisperSemantic Modality=true, Acoustic Modality=false2026.01 | 43.07 | 34.38 | |
| FASSemantic Modality=true, Acoustic Modality=true2026.01 | 40.03 | 33.39 | |
| C2SERSemantic Modality=true, Acoustic Modality=true2026.01 | 37.59 | 27.33 | |
| CLAPSemantic Modality=true, Acoustic Modality=false2026.01 | 34.63 | 26.57 | |
| Emotion2VecSemantic Modality=false, Acoustic Modality=false2026.01 | 33.53 | 29.01 | |
| WavLMSemantic Modality=true, Acoustic Modality=true2026.01 | 30.74 | 21.4 | |
| HuBERTSemantic Modality=true, Acoustic Modality=true2026.01 | 29.05 | 19.1 | |
| Qwen2.5-OmniSemantic Modality=true, Acoustic Modality=false2026.01 | 27.89 | 20.03 | |
| Qwen2-AudioSemantic Modality=true, Acoustic Modality=false2026.01 | 26.87 | 20.29 | |
| EnCodecSemantic Modality=false, Acoustic Modality=true2026.01 | 24.66 | 18.33 | |
| VibevoiceSemantic Modality=false, Acoustic Modality=true2026.01 | 22.47 | 17.95 | |
| MingTok-AudioSemantic Modality=false, Acoustic Modality=true2026.01 | 21.45 | 16.34 | |
| wav2vec 2.0Semantic Modality=true, Acoustic Modality=true2026.01 | 21.11 | 15.28 |