Speech Emotion Recognition on MELD-ST (DEU) (test)
53.32W-F1 ScoreERM-MinMaxGAP
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| ERM-MinMaxGAPModality=Multimodal (Speech + Transcription)2026.03 | 53.32 | 54.91 | 8.01 | 3.36 | 3.92 | 4.92 | 5.05 | |
| gpt4o-mini-audioModality=Multimodal (Speech + Transcription)2026.03 | 52.4 | 51.2 | 10.13 | 1.98 | 5.39 | 6.37 | 5.97 | |
| Voxtral-Mini-3BModality=Multimodal (Speech + Transcription)2026.03 | 48.46 | 53.33 | 7.14 | 1.47 | 0.95 | 0 | 2.39 | |
| ERM-MinMaxGAPModality=Unimodal (Speech only)2026.03 | 47.84 | 51.39 | 3.06 | 3.71 | 7.47 | 9.19 | 5.86 | |
| gpt4o-mini-audioModality=Unimodal (Speech only)2026.03 | 46.55 | 44.54 | 8.59 | 1.66 | 1.6 | 3.03 | 3.72 | |
| Voxtral-Mini-3BModality=Unimodal (Speech only)2026.03 | 45.71 | 45.65 | 9.6 | 2.5 | 4.09 | 4.21 | 5.1 | |
| kimi-audio-7bModality=Multimodal (Speech + Transcription)2026.03 | 44.16 | 42.69 | 4.14 | 1.67 | 4.53 | 5.15 | 3.87 | |
| kimi-audio-7bModality=Unimodal (Speech only)2026.03 | 39.03 | 38.43 | 10.75 | 3.04 | 4.27 | 2.13 | 5.05 | |
| Qwen2-AudioModality=Multimodal (Speech + Transcription)2026.03 | 32.18 | 26.85 | 10.25 | 1.96 | 3.22 | 1.49 | 4.23 | |
| Ultravox-0.4Modality=Multimodal (Speech + Transcription)2026.03 | 31.71 | 28.89 | 4.97 | 0.67 | 0.46 | 1.61 | 1.93 | |
| Qwen2-AudioModality=Unimodal (Speech only)2026.03 | 31.02 | 28.15 | 12.05 | 5.72 | 4.5 | 3.25 | 6.38 | |
| Ultravox-0.4Modality=Unimodal (Speech only)2026.03 | 27.97 | 25.56 | 1.68 | 0.5 | 1.92 | 0.43 | 1.13 |