Music Genre and Speech vs Music Classification on GTZAN
86.8Genre AccuracyHybrid BYOL-S/CvT
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Hybrid BYOL-S/CvTalpha:beta ratio=4:12022.06 | 86.8 | 92.3 | |
| Hybrid BYOL-S/CvTalpha:beta ratio=2:12022.06 | 86.4 | 94.6 | |
| Hybrid BYOL-S/CvTalpha:beta ratio=2:32022.06 | 86.1 | 93.8 | |
| Hybrid BYOL-S/Default2022.06 | 85.9 | 96.9 | |
| Hybrid BYOL-S/CvTalpha:beta ratio=1:12022.06 | 85.8 | 96.2 | |
| Hybrid BYOL-S/CvTalpha:beta ratio=3:22022.06 | 85.6 | 94.6 | |
| Hybrid BYOL-S/CvTalpha:beta ratio=1:22022.06 | 84.8 | 94.6 | |
| BYOL-Sencoder=CvT2022.06 | 84.2 | 97.7 | |
| BYOL-S++Pre-training dataset=BYOL-S++2022.06 | 83.9 | 93.8 | |
| BYOL-SPre-training dataset=BYOL-S2022.06 | 83.8 | 92.3 | |
| BYOL-Swindow size (s)=1.4252022.06 | 83.6 | 98.5 | |
| BYOL-APre-training dataset=BYOL-A2022.06 | 83.5 | 96.9 | |
| BYOL-Swindow size (s)=0.52022.06 | 83.5 | 96.9 | |
| BYOL-Swindow size (s)=22022.06 | 83.4 | 98.5 | |
| BYOL-S/CvT + OS2022.06 | 83.4 | 96.9 | |
| BYOL-Swindow size (s)=0.952022.06 | 82.5 | 96.2 | |
| Hybrid BYOL-S/CvTalpha:beta ratio=1:42022.06 | 82.2 | 95.3 | |
| openSMILE (OS)mode=OS only2022.06 | 78.2 | 97.6 | |
| wav2vec2baseline_type=HEAR baseline2022.06 | 78 | 92.3 | |
| BYOL-Sencoder=Resnetish-342022.06 | 77.4 | 96.9 | |
| BYOL-Sencoder=CLSTM2022.06 | 75.9 | 96.2 | |
| CREPEbaseline_type=HEAR baseline2022.06 | 64.5 | 86.7 |