Few-shot bioacoustic event detection at the DCASE 2022 challenge - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Few-shot bioacoustic event detection at the DCASE 2022 challenge

Résumé

Few-shot sound event detection is the task of detecting sound events, despite having only a few labelled examples of the class of interest. This framework is particularly useful in bioacoustics, where often there is a need to annotate very long recordings but the expert annotator time is limited. This paper presents an overview of the second edition of the few-shot bioacoustic sound event detection task included in the DCASE 2022 challenge. A detailed description of the task objectives, dataset, and baselines is presented, together with the main results obtained and characteristics of the submitted systems. This task received submissions from 15 different teams from which 13 scored higher than the baselines. The highest Fscore was of 60.2% on the evaluation set, which leads to a huge improvement over last year's edition. Highly-performing methods made use of prototypical networks, transductive learning, and addressed the variable length of events from all target classes. Furthermore, by analysing results on each of the subsets we can identify the main difficulties that the systems face, and conclude that few-show bioacoustic sound event detection remains an open challenge.
Fichier principal
Vignette du fichier
nolasco2022dcase.pdf (181.67 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03979696 , version 1 (08-02-2023)

Identifiants

  • HAL Id : hal-03979696 , version 1

Citer

I Nolasco, S Singh, E Vidaña-Vila, E Grout, J Morford, et al.. Few-shot bioacoustic event detection at the DCASE 2022 challenge. Detection and Classification of Acoustic Scenes and Events, Nov 2022, Nancy, France. ⟨hal-03979696⟩
22 Consultations
27 Téléchargements

Partager

Gmail Facebook X LinkedIn More