A finely annotated dataset for the automated acoustic identification of European Orthoptera and Cicadidae

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Mounting evidence points to widespread declines in insect abundance and diversity across European terrestrial ecosystems, highlighting an urgent need for effective large-scale monitoring methods. Passive acoustic monitoring enables the monitoring of sound-producing insects at an unprecedented temporal and spatial scale by remotely capturing sounds such as orthopteran stridulations and cicada timbalizations. However, current automated recognition tools for European insect sounds remain limited, and developing algorithms capable of reliably identifying diverse species requires large, ecologically heterogeneous acoustic datasets. Here we present a dataset of 11,224 recordings covering 193 orthopteran and 24 cicada species from North, Central, and temperate Western Europe. It combines coarsely labeled recordings, for which we can only infer the presence, at some point, of their target species (weak labeling), with finely annotated recordings that specify the time and frequency range of each insect sound (strong labeling). This dataset complements existing online resources and supports the advancement of automated acoustic classification for orthopterans and cicadas, aiding biodiversity monitoring efforts across Europe.
Funding Information
  • Association Nationale de la Recherche et de la Technologie (ANR-23-CPJ1-0174-01)
  • Association Nationale de la Recherche et de la Technologie (ANR-21-CE03-0002)
  • Association Nationale de la Recherche et de la Technologie (ANR-21-ESRE-0014)
  • Association Nationale de la Recherche et de la Technologie (ANR-23-CPJ1-0174-01)
  • The Slovenian Research and Innovation Agency (P1-0255)

This publication has 55 references indexed in Scilit: