Table 6 Overall multi-class classification performance for random forest and CNN
From: AudioPairBank: towards a large-scale tag-pair-based audio content analysis
Classifier | Pair | Features | Accuracy% |
|---|---|---|---|
RF | ANP | 13 MFCCs+ Δ + ΔΔ | 1.6 |
RF | VNP | 13 MFCCs+ Δ + ΔΔ | 4.5 |
CNN | ANP | 13 MFCCs+ Δ + ΔΔ | 2.1 |
CNN | VNP | 13 MFCCs+ Δ + ΔΔ | 7.4 |