Speech Emotion Recognition on ShEMO (test)
89.55WAWhisper Large V3
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Whisper Large V3Base Model=Whisper Large V3, Reference=Ma et al. (2024)2026.02 | 89.55 | 80.23 | |
| Whisper Small (QKV Pooling)Base Model=Whisper Small, Pooling=Multi-head QKV Pooling2026.02 | 89.19 | 83.07 | |
| WavLM LargeBase Model=WavLM Large, Reference=Ma et al. (2024)2026.02 | 87.13 | 71.72 | |
| Wav2vec 2.0 LargeBase Model=Wav2vec 2.0 Large, Reference=Nasersharif and Namvarpour (2024)2026.02 | 86.8 | 80.6 | |
| HuBERT LargeBase Model=HuBERT Large, Reference=Ma et al. (2024)2026.02 | 83.35 | 64.29 | |
| Data2vec 2.0 LargeBase Model=Data2vec 2.0 Large, Reference=Ma et al. (2024)2026.02 | 82.68 | 64.09 |