animal2vec and MeerKAT: A self-supervised transformer for rare-event raw audio input and a large-scale reference dataset for bioacoustics
This addresses a problem for bioacoustic researchers by providing tools to analyze large datasets with scarce annotations, though it is incremental in adapting existing deep learning techniques to a specific domain.
The paper tackles the challenge of analyzing bioacoustic data where animal vocalizations are rare by introducing animal2vec, a self-supervised transformer model, and MeerKAT, a large-scale annotated dataset. The model outperforms existing methods on benchmark datasets and performs well with limited labeled data.
Bioacoustic research, vital for understanding animal behavior, conservation, and ecology, faces a monumental challenge: analyzing vast datasets where animal vocalizations are rare. While deep learning techniques are becoming standard, adapting them to bioacoustics remains difficult. We address this with animal2vec, an interpretable large transformer model, and a self-supervised training scheme tailored for sparse and unbalanced bioacoustic data. It learns from unlabeled audio and then refines its understanding with labeled data. Furthermore, we introduce and publicly release MeerKAT: Meerkat Kalahari Audio Transcripts, a dataset of meerkat (Suricata suricatta) vocalizations with millisecond-resolution annotations, the largest labeled dataset on non-human terrestrial mammals currently available. Our model outperforms existing methods on MeerKAT and the publicly available NIPS4Bplus birdsong dataset. Moreover, animal2vec performs well even with limited labeled data (few-shot learning). animal2vec and MeerKAT provide a new reference point for bioacoustic research, enabling scientists to analyze large amounts of data even with scarce ground truth information.