Scholarlink

<p>The persisting threats on migratory bird populations highlight the urgent need for effective monitoring techniques that could assist in their conservation. Among these, passive acoustic monitoring is an essential tool, particularly for nocturnal migratory species that are difficult to track otherwise. This work presents the Nocturnal Bird Migration (NBM) dataset, a collection of 13,359 annotated vocalizations from 117 species of the Western Palearctic, compiled through a crowd-sourcing effort. The dataset includes precise time and frequency annotations gathered by dozens of bird enthusiasts across France, enabling the automatic extraction of vocalizations in audio recordings and, further, novel downstream acoustic analysis. This comprises the development of a novel two-stage deep object detection model optimized for audio data, achieving competitive accuracy on the 45 most represented species, comparable to state-of-the-art systems trained on substantially larger datasets.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An Open Dataset for the Acoustic Monitoring of Nocturnal Migratory Birds in Europe

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月21日

查看全文
  • Louis Airale,
  • Adrien Pajot,
  • Juliette Linossier

摘要

The persisting threats on migratory bird populations highlight the urgent need for effective monitoring techniques that could assist in their conservation. Among these, passive acoustic monitoring is an essential tool, particularly for nocturnal migratory species that are difficult to track otherwise. This work presents the Nocturnal Bird Migration (NBM) dataset, a collection of 13,359 annotated vocalizations from 117 species of the Western Palearctic, compiled through a crowd-sourcing effort. The dataset includes precise time and frequency annotations gathered by dozens of bird enthusiasts across France, enabling the automatic extraction of vocalizations in audio recordings and, further, novel downstream acoustic analysis. This comprises the development of a novel two-stage deep object detection model optimized for audio data, achieving competitive accuracy on the 45 most represented species, comparable to state-of-the-art systems trained on substantially larger datasets.