2023/09/16 by Ilyass Moummad, Moummad, Ilyass, Nicolas Farrugia +2 · 1 citation
Arts and Humanities · Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · #Adaptation (eye) #Animal Vocal Communication and Behavior #Artificial intelligence #Audio and Speech Processing (eess.AS) #Bioacoustics #Biology #Computer science #Diverse Musicological Studies #Engineering #Event (particle physics) #FOS: Computer and information sciences #FOS: Electrical engineering #Feature (linguistics) #Machine Learning (cs.LG) #Machine learning #Music and Audio Processing #Shot (pellet) #Sound (cs.SD) #Speech recognition #Task (project management) #Training (meteorology) #Transfer of learning #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2309.08971
openalex publication_date 2023/09/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Bioacoustic sound event detection allows for better understanding of animal behavior and for better monitoring biodiversity using audio. Deep learning systems can help achieve this goal, however it is difficult to acquire sufficient annotated data to train these systems from scratch. To address this limitation, the Detection and Classification of Acoustic Scenes and Events (DCASE) community has recasted the problem within the framework of few-shot learning and organize an annual challenge for learning to detect animal sounds from only five annotated examples. In this work, we regularize supervised contrastive pre-training to learn features that can transfer well on new target tasks with animal sounds unseen during training, achieving a high F-score of 61.52%(0.48) when no feature adaptation is applied, and an F-score of 68.19%(0.75) when we further adapt the learned features for each new target task. This work aims to lower the entry bar to few-shot bioacoustic sound event detection by proposing a simple and yet effective framework for this task, by also providing open-source code.