Speech Emotion Recognition on Speech Emotion Recognition (SER) Benchmarks
97.05AccuracyShah et al.
Evaluation results
| Method | Links | |
|---|---|---|
| Shah et al.Modality=A+EMA, Articulatory Features (AF)=true, Vocal Features (VF)=true, Validated on Multiple Languages (>1L)=false, Non-actor Dataset (NA)=true2026.06 | 97.05 | |
| Sharafi et al.Modality=A+V, Articulatory Features (AF)=false, Vocal Features (VF)=true, Validated on Multiple Languages (>1L)=false, Non-actor Dataset (NA)=false2026.06 | 95.48 | |
| MAJICModality=IMU+A, Articulatory Features (AF)=true, Vocal Features (VF)=true, Validated on Multiple Languages (>1L)=true, Non-actor Dataset (NA)=true2026.06 | 93 | |
| [71]Modality=A+EEG, Articulatory Features (AF)=true, Vocal Features (VF)=true, Validated on Multiple Languages (>1L)=false, Non-actor Dataset (NA)=true2026.06 | 89.7 | |
| [11]Modality=A+V+T, Articulatory Features (AF)=true, Vocal Features (VF)=true, Validated on Multiple Languages (>1L)=false, Non-actor Dataset (NA)=false2026.06 | 89 | |
| [71]Modality=A+V, Articulatory Features (AF)=true, Vocal Features (VF)=true, Validated on Multiple Languages (>1L)=false, Non-actor Dataset (NA)=false2026.06 | 87.89 | |
| [68]Modality=A, Articulatory Features (AF)=false, Vocal Features (VF)=true, Validated on Multiple Languages (>1L)=false, Non-actor Dataset (NA)=false2026.06 | 84.65 | |
| [70]Modality=A, Articulatory Features (AF)=false, Vocal Features (VF)=true, Validated on Multiple Languages (>1L)=false, Non-actor Dataset (NA)=false2026.06 | 80.44 | |
| [69]Modality=A, Articulatory Features (AF)=false, Vocal Features (VF)=true, Validated on Multiple Languages (>1L)=true, Non-actor Dataset (NA)=false2026.06 | 71.43 |