构建了热带鸟类声学数据集PteroSet，助力机器学习监测生物多样性。
A strongly annotated passive acoustic dataset for tropical bird monitoring
- 基于强标注的音频数据，统一使用COCO格式组织
- 包含563段录音、15372个时间-频率标注，覆盖168种鸟类
- 适合研究热带声景分析与鸟类检测的算法开发者
被动声学监测可在多样生态系统中实现持续、非侵入性的生物多样性评估。随着数据规模扩大，机器学习方法被广泛采用，但监督学习需依赖时间分辨标注数据，此类数据在复杂热带声景中仍十分稀缺。本文发布PteroSet，一个经过精心整理的中南美热带鸟类鸣叫数据集，采集于2023至2025年间哥伦比亚普图马约省波尔图米亚和马格达莱纳省皮维哈伊地区。数据集包含563段录音（总计73.62小时）和15,372个时间-频率标注，其中6,702个事件已鉴定至物种级别，覆盖168个物种。我们以类COCO JSON格式发布标注信息，整合音频文件、分类标签与注释，支持机器学习工作流。除提供标注数据外，PteroSet还作为真实场景基准，揭示热带声景的关键特征，如声学共现与跨站点域偏移。我们提供了二分类鸟类检测的深度学习基线模型，验证了该数据集的可用性及所面临的挑战。
原文摘要 · Abstract (English)
Passive acoustic monitoring enables continuous, non-invasive biodiversity assessment across diverse ecosystems. The scale of these datasets has driven the adoption of machine learning, with supervised approaches showing strong performance. However, supervised methods require time-resolved annotated datasets, which remain scarce, especially in complex tropical soundscapes. We present PteroSet, a curated dataset of strongly annotated Neotropical bird vocalizations recorded in Puerto Asis (Putumayo) and Pivijay (Magdalena), Colombia, between 2023 and 2025. The dataset comprises 563 recordings (73.62 h) and 15,372 time-frequency annotations, including 6,702 events identified to the species level across 168 species. We release the annotations in a COCO-inspired JSON schema that unifies audio files, taxonomic categories, and labels for machine learning workflows. Beyond providing annotated data, PteroSet serves as a realistic benchmark that highlights key characteristics of tropical soundscapes, including acoustic co-occurrence and domain shift across recording sites. We provide a deep learning baseline for binary bird detection, demonstrating PteroSet's usability and the challenges it presents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。