Speech Emotion Recognition On Crema D
評価指標
Accuracy
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | Accuracy | Paper Title | Repository |
|---|---|---|---|
| SepTr | 70.47 | SepTr: Separable Transformer for Audio Spectrogram Processing | - |
| CoordViT | 82.96 | CoordViT: A Novel Method of Improve Vision Transformer-Based Speech Emotion Recognition using Coordinate Information Concatenate | - |
| ResNet-18 + PyNADA | 65.15 | Non-linear Neurons with Human-like Apical Dendrite Activations | - |
| GRU | 55.01 | Visually Guided Self Supervised Learning of Speech Representations | - |
| SepTr + LeRaC | 70.95 | Learning Rate Curriculum | - |
| ResNet-18 + SPEL | 68.12 | Self-paced ensemble learning for speech and audio classification | - |
| Vertically long patch ViT | 94.07 | Accuracy enhancement method for speech emotion recognition from spectrogram using temporal frequency correlation and positional information learning through knowledge transfer | - |
| ConformerXL-P | 88.2 | BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition | - |
| ViT | 67.81 | AST: Audio Spectrogram Transformer | - |
0 of 9 row(s) selected.