SE-CRNN-16 with DualKD

Reported on 3 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio3 results

Sound Event DetectiononDESED
PSDS1· uses extra data· 2024-02-05
0.474
best: 0.587 (MAT-SED)
Dual Knowledge Distillation for Efficient Sound Event Detection arXiv:2402.02781
Sound Event DetectiononDESED
PSDS2· uses extra data· 2024-02-05
0.698
best: 0.896 (MAT-SED)
Dual Knowledge Distillation for Efficient Sound Event Detection arXiv:2402.02781
Sound Event DetectiononDESED
event-based F1 score· uses extra data· 2024-02-05
55.6
best: 63.4 (ATST-SED)
Dual Knowledge Distillation for Efficient Sound Event Detection arXiv:2402.02781