CAD classification on Noisy PCG dataset Fragment Level 1.0
73.9AccuracyMFCC Conformer
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| MFCC ConformerInput=Denoised, Noise segment rejection=true, Learning=Hybrid Contrastive2026.01 | 73.9 | 73.7 | 76.8 | 70.7 | 75.5 | 71.9 | 0.478 | |
| MFCC ConformerInput=Noisy, Noise segment rejection=false2026.01 | 71.2 | 70.9 | 77.5 | 64.2 | 73.9 | 67.5 | 0.425 | |
| Wav2Vec 2.0Input=Noisy2026.01 | 70.7 | 68.2 | 78.9 | 57.6 | 76.8 | 59.9 | 0.372 |