Overview of BirdCLEF 2020: Bird Sound Recognition in Complex Acoustic Environments

Stefan Kahl (1) , Mary Clapp (2) , W Alexander Hopping (1) , Hervé Goëau (3) , Hervé Glotin (4) , Robert Planqué (5) , Willem-Pier Vellinga (5) , Alexis Joly (6)

1 Cornell University [New York]
2 CS - UC Davis - Department of Computer Science [Univ California Davis]
3 UMR AMAP - Botanique et Modélisation de l'Architecture des Plantes et des Végétations
4 UTLN UFR Droit - Université de Toulon - Faculté de Droit de Toulon
5 Xeno-canto foundation
6 ZENITH - Scientific Data Management

Passive acoustic monitoring is a cornerstone of the assessment of ecosystem health and the improvement of automated assessment systems has the potential to have a transformative impact on global biodiversity monitoring, at a scale and level of detail that is impossible with manual annotation or other more traditional methods. The BirdCLEF challenge-as part of the 2020 LifeCLEF Lab [12]-focuses on the development of reliable detection systems for avian vocalizations in continuous soundscape data. The goal of the task is to localize and identify all audible birds within the provided soundscape test set. This paper describes the methodology of the conducted evaluation as well as the synthesis of the main results and lessons learned.

Mots clés: LifeCLEF; bird; song; call; species; retrieval; audio; collection; iden- tification; fine-grained classification; evaluation; benchmark; bioacoustics; eco- logical monitoring

Domaines: Intelligence artificielle [cs.AI]; Vision par ordinateur et reconnaissance de formes [cs.CV]; Multimédia [cs.MM]; Apprentissage [cs.LG]; Modélisation et simulation; Biodiversité et Ecologie; Environnement et Société

Stefan Kahl, Mary Clapp, W Alexander Hopping, Hervé Goëau, Hervé Glotin, et al.. Overview of BirdCLEF 2020: Bird Sound Recognition in Complex Acoustic Environments. CLEF 2020 - Conference and Labs of the Evaluation Forum, Sep 2020, Thessaloniki, Greece. ⟨hal-02989101⟩