Speech Emotion Recognition On Iemocap
評価指標
WA
WA CV
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 | WA | WA CV | Paper Title | Repository |
|---|---|---|---|---|
| Partially Fine-tuned HuBERT Large | 0.796 | 0.730 | A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding | - |
| SER with MTL | - | - | Speech Emotion Recognition with Multi-Task Learning | - |
| CNN - DARTS | - | - | Enhancing Speech Emotion Recognition Through Differentiable Architecture Search | |
| LSTM+FC | 0.755 | - | Speech Emotion Recognition Using Speech Feature and Word Embedding | |
| emoDARTS | - | 0.7803 | emoDARTS: Joint Optimisation of CNN & Sequential Neural Network Architectures for Superior Speech Emotion Recognition | |
| TAP | 0.810 | 0.742 | Speaker Normalization for Self-supervised Speech Emotion Recognition | - |
| CNN+LSTM | - | - | CNN+LSTM Architecture for Speech Emotion Recognition with Data Augmentation | - |
| SYSCOMB: BLSTMATT with CSA (session5) | 0.805 | - | Empirical Interpretation of Speech Emotion Perception with Attention Based Model for Speech Emotion Recognition | - |
0 of 8 row(s) selected.