ECOSoundSet: a finely annotated dataset for the automated acoustic identification of Orthoptera and Cicadidae in North, Central and temperate Western Europe. 2025

Here we present ECOSoundSet (European Cicadidae and Orthoptera Sound dataSet), a dataset containing 11,144 recordings of 201 orthopteran and 24 cicada species (219 and 26 subspecies, respectively) present in North, Central, and temperate Western Europe (Andorra, Belgium, Denmark, mainland France and Corsica, Germany, Ireland, Luxembourg, Monaco, Netherlands, United Kingdom, Switzerland), collected partly through targeted fieldwork in South France and Catalonia and partly through contributions from various European entomologists. The dataset is composed of a combination of coarsely labeled recordings, for which we can only infer the presence, at some point, of their target species (weak labeling), and finely annotated recordings, for which we know the specific time and frequency range of each insect sound present in the recording (strong labeling). We also provide a train/validation/test split of the annotated recordings, with respective approximate proportions of 0.8, 0.1 and 0.1, in order to facilitate their incorporation in the training and evaluation of deep learning algorithms. We posit that this dataset could serve as a meaningful complement to recordings already available online for the training of deep learning algorithms for the acoustic classification of orthopterans and cicadas in North, Central, and temperate Western Europe. How to cite: Funosas, D., Massol, E., Bas, Y., Schmidt, S., Arend, D., Gebhard, A., Barbaro, L., König, S., Font, R. C., Sannier, D., Deroussen, F., Sueur, J., Roesti, C., Trilar, T., Forstmeier, W., Roger, L., Matheu, E., Guzik, P., Barataud, J., Pelozuelo, L., Puissant, S., Mueller, S., Schuller, B., Montoya, J.M., Triantafyllopoulos, A., Cauchoix, M. (2025). ECOSoundSet: A finely annotated dataset for the automated acoustic identification of Orthoptera and Cicadidae in North, Central and temperate Western Europe (No. arXiv:2504.20776). arXiv. https://doi.org/10.48550/arXiv.2504.20776