Search

Menu
Search
in Ecology

A dataset of insect sounds from 459 species for bioacoustic machine learning

152 Views


Abstract

Automatic recognition of insect sound could help us understand changing biodiversity trends around the world—but insect sounds are challenging to recognize even for deep learning, due to the broad frequency ranges and limited amount of training data. We present a new dataset comprised of 26298 audio files (226.6 hours), from 459 species of Orthoptera (310 species) and Cicadidae (149 species). InsectSet459 is the first large-scale dataset of insect sound that is easily applicable for developing novel deep-learning methods. Its recordings were made with a variety of audio recorders using varying sample rates to capture the extremely broad range of frequencies that insects produce. We benchmark performance with two state-of-the-art deep learning classifiers, demonstrating good performance but also significant room for improvement in acoustic insect classification. This dataset can serve as a realistic test case for implementing insect monitoring workflows, and as a challenging basis for the development of audio representation methods that can handle highly variable frequencies and/or sample rates.

Data availability

The dataset can be downloaded from Zenodo under the CC 4.0 license (https://doi.org/10.5281/zenodo.14056457).

Code availability

The code that was used to download the source data from iNaturalist and xeno-canto, as well as curating and processing the data as described in the methods section is published on Github (https://github.com/mariusfaiss/InsectSet459). All code for benchmarking the dataset using the InsectEffNet (https://github.com/danstowell/insect_classifier_GDSC23_insecteffnet) and the PaSST models (https://github.com/kkoutini/PaSST) is also available on Github.

References

  1. Wagner, D. L., Grames, E. M., Forister, M. L., Berenbaum, M. R. & Stopak, D. Insect decline in the anthropocene: Death by a thousand cuts. Proceedings of the National Academy of Sciences, 118, https://doi.org/10.1073/pnas.2023989118 (2021).

  2. Montgomery, G. A. et al. Is the insect apocalypse upon us? how to find out. Biological Conservation 241, 108327, https://doi.org/10.1016/j.biocon.2019.108327 (2020).

    Google Scholar 

  3. van Klink, R. et al. Emerging technologies revolutionise insect ecology and monitoring. Trends in Ecology & Evolution https://doi.org/10.1016/j.tree.2022.06 (2022).

  4. Van Klink, R. et al. Towards a toolkit for global insect biodiversity monitoring. Philosophical Transactions of the Royal Society B 379, 20230101, https://doi.org/10.1098/rstb.2023.0101 (2024).

    Google Scholar 

  5. Kohlberg, A. B., Myers, C. R. & Figueroa, L. L. From buzzes to bytes: A systematic review of automated bioacoustics models used to detect, classify and monitor insects. Journal of Applied Ecology https://doi.org/10.1111/1365-2664.14630 (2024).

  6. Riede, K. & Balakrishnan, R. Acoustic monitoring for tropical insect conservation. bioRxiv https://www.biorxiv.org/content/early/2024/07/05/2024.07.03.601657 (2024).

  7. Riede, K. Acoustic profiling of Orthoptera: Present state and future needs. Journal of Orthoptera Research 27, 203–215 (2018).

    Google Scholar 

  8. Bennett, D., Nissen, H., Maschke, M. A., Reck, H. & Diekötter, T. Recent technological developments allow for passive acoustic monitoring of Orthoptera (grasshoppers and crickets) in research and conservation across a broad range of temporal and spatial scales. Basic and Applied Ecology 84, 147–157, https://doi.org/10.1016/j.baae.2025.03.004 (2025).

    Google Scholar 

  9. Pérez-Granados, C. BirdNet: applications, performance, pitfalls and future opportunities. Ibis (2023).

  10. Sethi, S. S. et al. Large-scale avian vocalization detection delivers reliable global biodiversity insights. Proceedings of the National Academy of Sciences 121, https://doi.org/10.1073/pnas.2315933121 (2024).

  11. Faiß, M. InsectSet47 & 66: Expanded datasets for automatic acoustic identification of insects (Orthoptera and Cicadidae) https://zenodo.org/record/7828438 (2023).

  12. Faiß, M. & Stowell, D. Adaptive Representations of Sound for Automatic Insect Recognition. PLOS Computational Biology arXiv:2304.12739, https://doi.org/10.1371/journal.pcbi.1011541 (2023).

  13. Vellinga, W.-P. & Planque, R. The Xeno-canto collection and its relation to sound recognition and classification https://ceur-ws.org/Vol-1391/166-CR.pdf (2015).

  14. iNaturalist. available from https://www.inaturalist.org accessed 09 august 2024.

  15. Chasmai, M., Shepard, A., Maji, S. & Horn, G. V. The iNaturalist sounds dataset. In Proceedings of the NeurIPS 2024 conference (Datasets and Benchmarks Track) https://doi.org/10.52202/079017-4213 (2024).

  16. Faiß, M. & Stowell, D. Insectset459: A large dataset for automatic acoustic identification of insects (orthoptera and cicadidae). Zenodo https://doi.org/10.5281/zenodo.14056457 (2025).

  17. Xeno-canto Foundation for Nature Sounds. Xeno-canto api query: Recordings of species in the “grasshoppers” group https://xeno-canto.org/api/2/recordings?query=grp:grasshoppers (2024).

  18. GBIF.Org User. Occurrence download https://www.gbif.org/occurrence/download/0058185-240626123714530 (2024).

  19. GBIF.Org User. Occurrence download https://www.gbif.org/occurrence/download/0058173-240626123714530 (2024).

  20. Baker, E., Price, B. W., Rycroft, S. D., Hill, J. & Smith, V. S. BioAcoustica: a free and open repository and analysis platform for bioacoustics. Database 2015, bav054–bav054, https://doi.org/10.1093/database/bav054 (2015).

    Google Scholar 

  21. Faiß, M. InsectSet32: Dataset for automatic acoustic identification of insects (Orthoptera and Cicadidae) https://zenodo.org/record/7072196 (2022).

  22. Döring, M., Jeppesen, T. & Bánki, O. Introducing checklistbank: An index and repository for taxonomic data. Biodiversity Information Science and Standards https://doi.org/10.3897/biss.6.93938 (2022).

  23. Borowiec, M. L. et al. Deep learning as a tool for ecology and evolution. Methods in Ecology and Evolution 13, 1640–1660, https://doi.org/10.1111/2041-210X.13901 (2022).

    Google Scholar 

  24. Odé, B. et al. A list of sound producing European grasshoppers and the availability of their sounds in Xeno-canto 95–130, https://doi.org/10.62323/a100191 (2025).

  25. SINA. Singing Insects of North America. https://orthsoc.org/sina/index.htm (2023).

  26. Stowell, D. Computational bioacoustics with deep learning: a review and roadmap. PeerJ 10, https://doi.org/10.48550/arXiv.2112.06725 (2022).

  27. Ghani, B. et al. Generalization in birdsong classification: impact of transfer learning methods and dataset characteristics https://arxiv.org/abs/2409.15383 (2024).

  28. Tan, M. & Le, Q. Efficientnetv2: Smaller models and faster training. In International conference on machine learning, 10096–10106, https://arxiv.org/abs/2104.00298 (PMLR, 2021).

  29. Kahl, S., Wood, C. M., Eibl, M. & Klinck, H. BirdNET: A deep learning solution for avian diversity monitoring. Ecological Informatics, 61, 101236, https://doi.org/10.1016/j.ecoinf.2021.101236 (2021).

  30. Dolbear, A. E. The Cricket as a Thermometer 31, 970–971 https://www.journals.uchicago.edu/doi/10.1086/276739 (1897).

  31. Greenfield, M. D. Acoustic Communication in Orthoptera (CAB INTERNATIONAL, 1997).

Download references

Acknowledgements

We thank the many contributors to the xeno-canto and iNaturalist collections, for sharing their recordings, without whom this work would not have been possible. We highlight the following users who each contributed over 500 recordings: Baudewijn Odé (also for project advice), Christie (iNaturalist username), Joel Poyitt, K.-G. Heller, S. Ingrisch, Cedric Mroczko. The InsectEffNet classifier was developed as part of a CapGemini “Global Data Science Challenge”, supported by Amazon Web Services. The classifier code was contributed by a CapGemini team and authored by Raffaela Heily, Lukas Kemetinger, Dominik Lemm and Lucas Unterberger. It is used here with permission. MF was supported by the EU MSCA Doctoral Network Bioacoustic AI (BioacAI, 101071532). BG was supported by EU-funded Horizon projects MAMBO (101060639), GUARDEN (101060693) and TETTRIs (101081903).

Funding

Open Access funding enabled and organized by Projekt DEAL.

Author information

Authors and Affiliations

  1. Department for the Ecology of Animal Societies, Max Planck Institute of Animal Behavior, Konstanz, Germany

    Marius Faiß

  2. International Max Planck Research School for Quantitative Behavior, Ecology and Evolution, Konstanz, Germany

    Marius Faiß

  3. Department of Biology, University of Konstanz, Konstanz, Germany

    Marius Faiß

  4. Naturalis Biodiversity Centre, Leiden, The Netherlands

    Burooj Ghani & Dan Stowell

  5. Department of Cognitive Science and Artificial Intelligence, Tilburg University, Tilburg, The Netherlands

    Dan Stowell

Authors

  1. Marius Faiß
    View author publications

    Search author on:PubMed Google Scholar

  2. Burooj Ghani
    View author publications

    Search author on:PubMed Google Scholar

  3. Dan Stowell
    View author publications

    Search author on:PubMed Google Scholar

Contributions

M.F. and D.S. conceived the data selection process, wrote code for the data processing and figure creation, wrote and edited the draft; M.F. wrote code for downloading, processing and annotating the data; D.S. wrote the code for benchmarking the InsectEffNet model; B.G. developed the PaSST-based model; all authors reviewed the final draft.

Corresponding author

Correspondence to
Marius Faiß.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary information: Classifier performance (download PDF )

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.

Reprints and permissions

About this article

Cite this article

Faiß, M., Ghani, B. & Stowell, D. A dataset of insect sounds from 459 species for bioacoustic machine learning.
Sci Data (2026). https://doi.org/10.1038/s41597-026-07123-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1038/s41597-026-07123-4

Source: Ecology - nature.com

Soil classification in the Sudan Savanna using sentinel products and topographic information with machine learning models

Pathways to cost-optimal and net-zero emissions irrigation in the United States

This portal is not a newspaper as it is updated without periodicity. It cannot be considered an editorial product pursuant to law n. 62 of 7.03.2001. The author of the portal is not responsible for the content of comments to posts, the content of the linked sites. Some texts or images included in this portal are taken from the internet and, therefore, considered to be in the public domain; if their publication is violated, the copyright will be promptly communicated via e-mail. They will be immediately removed.

Back to Top
Close