Audio Classification On Dcase
Metrics
PRE-TRAINING DATASET
Top-1 Accuracy
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | PRE-TRAINING DATASET | Top-1 Accuracy |
|---|---|---|
| self-supervised-audio-visual-representation | Kinetics-400 | 96 |
| self-supervised-audio-visual-representation | AudioSet | 97 |
| self-supervised-learning-by-cross-modal-audio | IG-Random | 95 |
| self-supervised-learning-by-cross-modal-audio | AudioSet | 95 |
| self-supervised-audio-visual-representation | Kinetics-Sound | 93 |