UrbanSound
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Audio Classification | Urbansound8K | Accuracy97.5 | 126 | |
| Urban Sound Classification | UrbanSound 8k | Accuracy87.2 | 29 | |
| Urban Sound Classification | UrbanSound8K (test) | Accuracy88.8 | 28 | |
| Audio Classification | UrbanSound8K (official 10 fold split) | Accuracy (%)97.96 | 23 | |
| Urban Sound Classification | UrbanSound 8k | Normalized Score89.3 | 20 | |
| Environmental Sound Classification | UrbanSound8k | Accuracy60.94 | 16 | |
| Audio Classification | UrbanSound8K In-Domain | AI40.85 | 12 | |
| Recognition | UrbanSound (Urban-S) | Top-1 Accuracy71.6 | 8 | |
| Hallucination Mitigation | UrbanSound8K | HR (%)95.98 | 6 | |
| Audio Classification | UrbanSound8K (train test) | mAP89.24 | 6 | |
| Interpretation for Audio Classification | UrbanSound8K STFT-Masking, LJ-Speech contamination (test) | Attribution Importance (AI)38.74 | 6 | |
| Interpretation for Audio Classification | UrbanSound8K Mel-Masking LJ-Speech contamination (test) | AI36.24 | 6 | |
| Interpretation for Audio Classification | UrbanSound8K STFT-Masking White Noise contamination (test) | Attribution Importance Score46.51 | 6 | |
| Audio Classification | UrbanSound8K 100 labels | Top-1 Error Rate0.3497 | 6 | |
| Source Separation | UrbanSound8k fold 10 (test) | Mean SDR12.2 | 6 | |
| Environmental audio classification | UrbanSound8K (cross-validation) | Accuracy82 | 5 | |
| Anomaly Detection | UrbanSound | Inference Time (s)0.0103 | 5 | |
| Anomaly Detection | UrbanSound8K (test) | AUC-ROC0.9142 | 5 | |
| Urban environmental sound classification | UrbanSound-8k | Standardized Score0.53 | 3 | |
| Audio Classification | UrbanSound8K (val) | Metric- | 0 |
Showing 20 of 20 rows