Hybrid Disagreement-Diversity Active Learning for Bioacoustic Sound Event Detection

2025/05/27 by Shiqi Zhang, Tuomas Virtanen, Zhang, Shiqi +1
Biochemistry, Genetics and Molecular Biology · Computer Science · Environmental Science · #Animal Vocal Communication and Behavior #Artificial Intelligence (cs.AI) #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Music and Audio Processing #Sound (cs.SD) #Wildlife-Road Interactions and Conservation #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2505.20956

openalex publication_date 2025/05/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Bioacoustic sound event detection (BioSED) is crucial for biodiversity conservation but faces practical challenges during model development and training: limited amounts of annotated data, sparse events, species diversity, and class imbalance. To address these challenges efficiently with a limited labeling budget, we apply the mismatch-first farthest-traversal (MFFT), an active learning method integrating committee voting disagreement and diversity analysis. We also refine an existing BioSED dataset specifically for evaluating active learning algorithms. Experimental results demonstrate that MFFT achieves a mAP of 68% when cold-starting and 71% when warm-starting (which is close to the fully-supervised mAP of 75%) while using only 2.3% of the annotations. Notably, MFFT excels in cold-start scenarios and with rare species, which are critical for monitoring endangered species, demonstrating its practical value.

Citations

• Towards Deep Active Learning in Avian Bioacoustics
• animal2vec and MeerKAT: A self-supervised transformer for rare-event raw audio input and a large-scale reference dataset for bioacoustics
• From Weak to Strong Sound Event Labels using Adaptive Change-Point Detection and Active Learning
• Regularized Contrastive Pre-training for Few-shot Bioacoustic Sound Detection
• Understanding Uncertainty Sampling
• Margin-based sampling in high dimensions: When being active is less efficient than staying passive
• Few-shot bioacoustic event detection at the DCASE 2022 challenge
• Active Learning for Sound Event Detection
• PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition

Related

• Mind the Domain Gap: a Systematic Analysis on Bioacoustic Sound Event Detection
• What Matters for Bioacoustic Encoding
• Few-shot Bioacoustic Event Detection with Machine Learning Methods
• Few-shot bioacoustic event detection at the DCASE 2023 challenge
• Aggregation Strategies for Efficient Annotation of Bioacoustic Sound Events Using Active Learning