CRNN (WildDESED + Curriculrm learning)

Reported on 5 benchmarks across 1 task · 1 paper · 3 SOTA

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

Audio5 results

Sound Event DetectiononWildDESED
PSDS1 (-5dB)· 2024-07-04
0.049
best: 0.134 (CRNN (with BEATs + Separation))
SOTA
WildDESED: An LLM-Powered Dataset for Wild Domestic Environment Sound Event Detection System arXiv:2407.03656
Sound Event DetectiononWildDESED
PSDS1 (0dB)· 2024-07-04
0.114
best: 0.219 (CRNN (with BEATs + Separation))
SOTA
WildDESED: An LLM-Powered Dataset for Wild Domestic Environment Sound Event Detection System arXiv:2407.03656
Sound Event DetectiononWildDESED
PSDS1 (5dB)· 2024-07-04
0.175
best: 0.291 (CRNN (with BEATs + Separation))
SOTA
WildDESED: An LLM-Powered Dataset for Wild Domestic Environment Sound Event Detection System arXiv:2407.03656
Sound Event DetectiononWildDESED
PSDS1 (10dB)· 2024-07-04
0.212
best: 0.356 (CRNN (with BEATs + Separation))
WildDESED: An LLM-Powered Dataset for Wild Domestic Environment Sound Event Detection System arXiv:2407.03656
Sound Event DetectiononWildDESED
PSDS1 (Clean)· 2024-07-04
0.265
best: 0.5 (CRNN (with BEATs))
WildDESED: An LLM-Powered Dataset for Wild Domestic Environment Sound Event Detection System arXiv:2407.03656