Speech Emotion Recognition on IEMOCAP and MELD Average
69.55Average AccuracyOurs (Sys. 10)
Evaluation results
| Method | Links | |
|---|---|---|
| Ours (Sys. 10)SED=true, Domain SFT=true, Confidence Score Data Selection=90%, RL-based SED Rectification=true2026.06 | 69.55 | |
| VIB-Emo2026.06 | 65.76 | |
| BLSP-Emo2026.06 | 63.32 | |
| Audio-Flamingo-32026.06 | 60.69 | |
| Kimi-Audio2026.06 | 58.68 | |
| OSUM-EChat2026.06 | 49.55 | |
| Step-Audio-R12026.06 | 48.87 | |
| Qwen2-Audio2026.06 | 46.87 |