Overview of BirdCLEF 2021: Bird call identification in soundscape recordings

Kahl Stefan, Denton Tom, Klinck Holger, Glotin Hervé, Goeau Hervé. 2021. Overview of BirdCLEF 2021: Bird call identification in soundscape recordings. In : Proceedings of the Working Notes of CLEF 2021. Faggioli Guglielmo (ed.), Ferro Nicola (ed.), Joly Alexis (ed.), Maistro Maria (ed.), Piroi Florina (ed.). s.l. : CEUR-WS, 1437-1450. (CEUR Workshop Proceedings, 2936) Conference and Labs of the Evaluation Forum (CLEF 2021). 12, Bucharest, Roumanie, 21 Septembre 2021/24 Septembre 2021.

Résumé : Conservation of bird species requires detailed knowledge of their spatiotemporal occurrence and distribution patterns. Over the past decade, passive acoustic monitoring (PAM) has become an essential tool to collect data on birds on ecologically relevant scales. However, these PAM efforts generate extensive datasets, and their comprehensive analysis remains challenging. Improved and fully automated acoustic analysis frameworks are needed to advance the field of avian conservation. The 2021 BirdCLEF challenge focused on developing and assessing automated analysis frameworks for avian vocalizations in continuous soundscape data. The primary task of the challenge was to detect and identify all bird calls within the hidden test dataset. This paper describes how the various algorithms were evaluated and synthesizes the results and lessons learned.

Mots-clés libres : LifeCLEF, Bird, Song, Call, Species, Retrieval, Audio, Collection, Identification, Fine-grained classification, Evaluation, Benchmark, Bioacoustics, Passive Acoustic Monitoring

Auteurs et affiliations

• Kahl Stefan, Cornell University (USA)
• Denton Tom, Google LLC (USA)
• Klinck Holger, Cornell University (USA)
• Glotin Hervé, Université de Toulon et du Var (FRA)
• Goeau Hervé, CIRAD-BIOS-UMR AMAP (FRA)

Source : Cirad-Agritrop (https://agritrop.cirad.fr/612697/)

Métriques

[ Page générée et mise en cache le 2025-09-21 ]