Belarusian bird acoustic recognition: data preparation and model training process

The issue of substantial labor and time demands for monitoring bird species diversity and range changes, especially in developing countries, invites novel technological solutions. The recent advancements in machine learning (ML) have led to breakthroughs in AI-based data processing, including tools for automated passive acoustic monitoring (PAM) that utilize on-site bird vocalizations. Here we describe our preliminary results and difficulties encountered when developing an EfficientNetB3-based model for a PAM system to monitor bird diversity in the forested areas of interest in Belarus. A novel dataset of bird vocalizations from Eastern Europe, processed and converted into mel-spectrograms allowed us to achieve a respectable f1-scores (>0.9) in tests for certain species such as nightjar and nutcracker. However, the overall score (0.52) for the 116 species of interest was unacceptably low. Further testing with a more specialized dataset allowed us to determine that the problem lies with the peculiarities of species, and is not limited to species with complex vocalizations. We hypothesize that model overfitting to specific vocalization signals may be one of the main causes. Additionally, certain species require a thorough coverage of their vocalization diversity in the dataset.

1. Priyadarshani N., Marsland S., Castro I. Automated birdsong recognition in complex acoustic environments: a review. Journal of Avian Biology, 2018, vol. 49, no. 5, p. jav-01447. https://doi.org/10.1111/jav.01447

2. Klein D. J., Mckown M. W., Tershy B. R. Deep Learning for Large Scale Biodiversity Monitoring. Bloomberg Data for Good Exchange. New York, 2015. https://doi.org/10.13140/RG.2.1.1051.7201

3. Miao Z., Gaynor K. M., Wang J., Liu Z., Muellerklein O., Norouzzadeh M. S., McInturff A., Bowie R. C. K., Nathan R., Yu S. X., Getz W. M. Insights and approaches using deep learning to classify wildlife. Scientific Reports, 2019, vol. 9, no. 1, art. 8137. https://doi.org/10.1038/s41598-019-44565-w

4. Sharma S., Sato K., Gautam B. P. A Methodological Literature Review of Acoustic Wildlife Monitoring Using Artificial Intelligence Tools and Techniques. Sustainability, 2023, vol. 15, no. 9, art. 7128. https://doi.org/10.3390/su15097128

5. Wood C. M., Kahl S., Rahaman A., Klinck H. The machine learning–powered BirdNET App reduces barriers to global bird research by enabling citizen science participation. PLOS Biology, 2022, vol. 20, no 6, p. e3001670. https://doi.org/10.1371/journal.pbio.3001670

6. Bota G., Manzano-Rubio R., Catalán L., Gómez-Catasús J., Pérez-Granados C. Hearing to the Unseen: AudioMoth and BirdNET as a Cheap and Easy Method for Monitoring Cryptic Bird Species. Sensors, 2023, vol. 23, no. 16, art. 7176. https://doi.org/10.3390/s23167176

7. Ware L., Mahon C. L., McLeod L., Jetté J.-F. Artificial intelligence (BirdNET) supplements manual methods to maximize bird species richness from acoustic data sets generated from regional monitoring. Canadian Journal of Zoology, 2023, vol. 101, no. 12, pp. 1031–1051. https://doi.org/10.1139/cjz-2023-0044

8. Karlionova N. V., Borodin A. V., Samusenko I. E., Nikiforov M. E. Records of rare birds approved by the Belarusian Ornithofaunistic Commission in 2021 and 2022. Zoologicheskie chteniya: sbornik nauchnykh statei, posvyashchennyi 125-letiyu doktora biologicheskikh nauk Ivana Nikolaevicha Serzhanina, 22–24 marta 2023 goda, Grodno [Zoological readings: a collection of scientific articles dedicated to the 125th anniversary of Doctor of Biological Sciences Ivan Nikolaevich Serzhanin, March 22–24, 2023, Grodno]. Grodno, 2023, рр. 113–125 (in Russian).

9. Vellinga W.-P. Xeno-canto – Bird sounds from around the world. Available at: https://www.gbif.org/dataset/b1047888-ae524179-9dd5-5448ea342a24 (accessed 01.11.2024).

10. Fonseca E., Favory X., Pons J., Font F., Serra X. FSD50K: An Open Dataset of Human-Labeled Sound Events. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2022, vol. 30, pp. 829–852. https://doi.org/10.1109/TASLP.2021.3133208

11. Zianouka Y., Bialiauski D., Kajharodava L., Trafimau A., Chachlou V., Hetsevich J., Zahariev V., Zhaksylyk K. Developing Birds Sound Recognition System Using an Ontological Approach. Open Semantic Technologies for Intelligent Systems: Research Papers Collection. Minsk, 2023, iss. 7, pp. 165–170. Available at: https://libeldoc.bsuir.by/bitstream/123456789/51271/1/Zianouka_Developing.pdf (accessed 01.11.2024).

12. Koh C.-Y., Chang J.-Y., Tai C.-L., Huang D.-Y., Hsieh H.-H., Liu Y.-W. Bird Sound Classification Using Convolutional Neural Networks. Working Notes of CLEF 2019 – Conference and Labs of the Evaluation Forum (CLEF 2019), Lugano, Switzerland, September 9–12, 2019. Available at: https://ceur-ws.org/Vol-2380/paper_68.pdf (accessed 01.11.2024).

13. Sevilla A., Glotin H. Audio Bird Classification with Inception-v4 extended with Time and Time-Frequency Attention Mechanisms. Working Notes of CLEF 2017 – Conference and Labs of the Evaluation Forum, Dublin, Ireland, September 11–14, 2017. Available at: https://ceur-ws.org/Vol-1866/paper_177.pdf (accessed 01.11.2024).

14. Chollet F. Keras 3 API Documentation. Available at: https://keras.io/applications (accessed 01.11.2024).

15. Tan M., Le Q. V. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. International confe rence on machine learning. Long Beach, 2019. Available at: https://proceedings.mlr.press/v97/tan19a/tan19a.pdf (accessed 01.11.2024).

16. Kahl S., Denton T., Klinck H., Reers H., Cherutich F., Glotin H., Goëau H., Vellinga W.-P., Planqué R., Joly A. Overview of BirdCLEF 2023: Automated Bird Species Identification in Eastern Africa. Working Notes of the Conference and Labs of the Evaluation Forum (CLEF 2023), Thessaloniki, Greece, September 18th to 21st, 2023. Available at: https://ceur-ws.org/Vol-3497/paper-164.pdf (accessed 01.11.2024).