Automation of bird voice signal analysis

Objectives. The purpose of the work is to create an experimental software for automated recognition of voice signals, which has the capabilities of long-term round-the-clock and round-the-season monitoring of animal species diversity in selected habitats and ecosystems.

Methods. The work uses methods of deep machine learning of convolutional neural networks trained on mel-spectrograms of bird vocalizations, which are built using fast Fourier transform.

Results. The process, methods and approaches to training a deep machine learning model for a system of passive acoustic monitoring of bird populations in Belarus are described, as well as the difficulties identified during testing of the software prototype and the results that were achieved.

Conclusion. A working prototype of the software for automatic recognition of animal (bird) voice signals is presented. It performs the analysis of acoustic recordings of bird voices with the issue of probabilistic assessment of species belonging to animal vocalizations present in the recordings. The software is aimed at increasing the efficiency of bird monitoring, which ensures the implementation of conservation and research activities based on accurate and up-to-date data on species distribution.

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. Available at: https://nsojournals.onlinelibrary.wiley.com/doi/full/10.1111/jav.01447 (accessed 19.03.2021).

2. 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, r. 7128 . https://doi.org/10.3390/su15097128.

3. Briggs F., Raich R., Fern X. Z. Audio classification of bird species: a statistical manifold approach. 2009 Ninth IEEE International Conference on Data Mining, Miami Beach, FL, USA, 6-9 December 2009. Miami Beach, 2009, pp. 51-60.

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

5. Miao Z., Gaynor K. M., Wang J., Liu Z., Muellerklein O., Norouzzadeh M. S. Insights and approaches using deep learning to classify wildlife. Scientific Reports, 2019, vol. 9, no. 1. Available at: https://www.nature. com/articles/s41598-019-44565-w (accessed 13.02.2021). https://doi.org/10.1038/s41598-019-44565-w.

6. Hetsevich Yu. S., Dydo O. V., Bialiauski D. A., Zjanowka Ja. S., Ljucich M. S., …, Nazaraw U. U. Technologies of automatic speech processing and analysis using artificial intelligence. Doklady II Foruma IT-Akademgrada «Iskusstvennyj intellekt v Belarusi» [Reports of the II IT Academy Forum "Artificial Intelligence in Belarus", Minsk, 12-13 October 2023]. Minsk, The United Institute of Informatics Problems of the National Academy of Sciences of Belarus, 2023, pp. 71-78 (In Bel).

7. Klein D. J., Mckown M. W., Tershy B. R. Deep learning for large scale biodiversity monitoring. Bloomberg Data for Good Exchange Conference, New York, NY, USA, 28 September 2015. New York, 2015, 7 r. https://doi.org/10.13140/RG.2.1.1051.7201.

8. 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. The Canadian Journal of Zoology, 2023, vol. 101, no. 12, pp. 1031-1051.

9. Stowell D., Plumbley M. D. An open dataset for research on audio field recording archives: freefield1010, 2013. Available at: https://arxiv.org/abs/1309.5275 (accessed 06.06.2024). https://doi.org/10.48550/arXiv.1309.5275.

10. 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, 10 r. https://doi.org/10.48550/arXiv.1309.5275.

11. Karlionova N. V., Borodin A. V., Samusenko I. E., Nikiforov M. Y. The Belarusian list of bird species approved by the Belarusian Ornitho-Faunistic Commission for 2021 and 2022. Zoological Readings, Grodno, Grodnenskij gosudarstvennyj universitet imeni Janki Kupaly, 2023, r. 113.

12. Gaidurov S. A., Latyshevich D. I, Bakunovich A. A., Kaigorodova L. I., Khokhlov V. A., …, Hetsevich Yu. S. A database model for automated recognition of animal voice signals. Razvitie informatizacii i gosudarstvennoj sistemy nauchno-tehnicheskoj informacii RINTI-2022 : doklady KhKhI Mezhdunarodnoj nauchno-tehnicheskoj konferencii, Minsk, 17 nojabrja 2022 g. [Development of Informatization and the State System of Scientific and Technical Information (RINTI-2022) : Reports of the XXI International Scientific and Technical Conference, Minsk, 17 November 2022], The United Institute of Informatics Problems of the National Academy of Sciences of Belarus, 2022, pp. 236-240 (In Bel.).

13. Stowell D. Computational bioacoustics with deep learning: a review and roadmap. PeerJ, 2022, vol. 10, r. 46.

14. Fonseca E., Favory X., Pons J., Font F., Serra X. FSD50K: an open dataset of human-labeled sound events. ACM Transactions on Audio, Speech, and Language Processing, 2022, vol. 30, pp. 829-852.

15. 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, vol. 23, no. 16, 11 p. https://doi.org/10.3390/s23167176.

16. Tan M., Le Q. V. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the 36th International Conference on Machine Learning, ICML 2019, Long Beach, 9-15 June 2019. Long Beach, 2019, rr. 6105-6114.

17. Wang Y., Rosli M. M., Musa N., Li F. Multi-class imbalanced data classification: a systematic mapping study. Engineering, Technology & Applied Science Research, 2024, vol. 14, rr. 14183-14190. https://doi.org/10.48084/etasr.7206

18. Mao J.-X., Hang J.-Y., Zhang M.-L. Learning label-specific multiple local metrics for multi-label classification. Thirty-Third International Joint Conference on Artificial Intelligence {IJCAI-24}, Jeju, Korea, 3-9 Aug. 2024. Jeju, 2024, pp. 4742-4750. https://doi.org/10.24963/ijcai.2024/524.

19. Jia B.-B., Liu J.-Y., Zhang M.-L. Towards exploiting linear regression for multi-class/multi-label classification: an empirical analysis. International Journal of Machine Learning and Cybernetics, March 2024, vol. 15, rr. 3671-3700. https://doi.org/10.1007/s13042-024-02114-6.

20. ZianoukaYa., Bialiauski D., Kajharodava L., Chachlou V., Hetsevich Yu., …, Zhaksylyk K. Developing birds sound recognition system using an ontological approach. Open Semantic Technologies for Intelligent Systems, Minsk, Belarusian State University of Informatics and Radioelectronics, 2023, iss. 7, pp. 165-170.

21.