DroneAudioDataset
A public audio dataset for research on drone acoustic detection, containing drone and non-drone audio clips. It is commonly used to evaluate the performance of acoustic detection models.
Timeline (last 90 days)
The DroneAudioDataset contains 11,704 one-second audio clips, of which 1,332 drone clips come from 257 five-second chunks split from 7 recordings.
Of the non-drone clips in the DroneAudioDataset, 96.4% originate from the ESC-50 sound dataset.
Under a group-disjoint source protocol, the dual-view stacking model achieves an average accuracy of 95.29% with a standard deviation of 1.62 percentage points (15 test folds).
The dual-view stacking model has a specificity of 98.29% and an area under the ROC curve of 0.990.
All Facts (4)
The DroneAudioDataset contains 11,704 one-second audio clips, of which 1,332 drone clips come from 257 five-second chunks split from 7 recordings.
50%UnverifiedOf the non-drone clips in the DroneAudioDataset, 96.4% originate from the ESC-50 sound dataset.
50%UnverifiedUnder a group-disjoint source protocol, the dual-view stacking model achieves an average accuracy of 95.29% with a standard deviation of 1.62 percentage points (15 test folds).
50%UnverifiedThe dual-view stacking model has a specificity of 98.29% and an area under the ROC curve of 0.990.
50%