BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics
This provides a versatile resource for researchers in bioacoustics and audio classification, though it is incremental as it builds upon existing datasets like AudioSet.
The authors tackled the scarcity of large-scale benchmark datasets in audio classification by introducing BirdSet, a dataset for avian bioacoustics that includes over 6,800 recording hours and nearly 10,000 classes, and they benchmarked six deep learning models across three training scenarios.
Deep learning (DL) has greatly advanced audio classification, yet the field is limited by the scarcity of large-scale benchmark datasets that have propelled progress in other domains. While AudioSet is a pivotal step to bridge this gap as a universal-domain dataset, its restricted accessibility and limited range of evaluation use cases challenge its role as the sole resource. Therefore, we introduce BirdSet, a large-scale benchmark dataset for audio classification focusing on avian bioacoustics. BirdSet surpasses AudioSet with over 6,800 recording hours ($\uparrow\!17\%$) from nearly 10,000 classes ($\uparrow\!18\times$) for training and more than 400 hours ($\uparrow\!7\times$) across eight strongly labeled evaluation datasets. It serves as a versatile resource for use cases such as multi-label classification, covariate shift or self-supervised learning. We benchmark six well-known DL models in multi-label classification across three distinct training scenarios and outline further evaluation use cases in audio classification. We host our dataset on Hugging Face for easy accessibility and offer an extensive codebase to reproduce our results.