Speech Emotion Recognition on IEMOCAP Speaker-dependent random train-test split
81WAHuBERT Large + Ours (TAP)
Evaluation results
| Method | Links | |
|---|---|---|
| HuBERT Large + Ours (TAP)Backbone=HuBERT Large, Strategy=Train all parameters (TAP)2022.02 | 81 | |
| HuBERT Large + Ours (SNP)Backbone=HuBERT Large, Strategy=Speaker normalization projector (SNP)2022.02 | 79.9 | |
| HuBERT LargeBackbone=HuBERT Large2022.02 | 78.3 | |
| MOMA2022.02 | 74.8 | |
| HuBERT Base + Ours (SNP)Backbone=HuBERT Base, Strategy=Speaker normalization projector (SNP)2022.02 | 72.8 | |
| DS-LSTM2022.02 | 72.7 | |
| HuBERT Base + Ours (TAP)Backbone=HuBERT Base, Strategy=Train all parameters (TAP)2022.02 | 72.4 | |
| MDRE2022.02 | 71.8 | |
| HuBERT BaseBackbone=HuBERT Base2022.02 | 71.2 |