Acoustic Shield: Lightweight Neural Network for Audio-Based Drone Detection and Classification

Document Type : Original Article

Author

M.Sc. in Artificial Intelligence & Robotics, Faculty of Computer Engineering, Malek ashtar University, Tehran, Iran.

Abstract

The widespread use of UAVs has intensified the need for advanced security measures to prevent unauthorized airspace intrusions and mitigate potential threats. Audio-based drone detection systems, which leverage the unique acoustic signatures of drones, offer a viable solution for remote monitoring and surveillance in sensitive environments such as military zones, secured facilities, and urban areas. In this paper, we propose a powerful framework based on a lightweight deep neural network architecture derived from ConvNeXt for accurate and real-time acoustic drone detection and classification. The proposed model is trained and evaluated on a diverse collection of drone and environmental audio recordings to ensure high performance and generalization across various conditions. Experimental results demonstrate the model’s outstanding ability to accurately detect and classify a wide range of drones in acoustically complex environments, while also maintaining low latency suitable for real-time applications. Moreover, the proposed multi-task model outperforms existing methods and proves to be a practical solution for deployment in resource-constrained audio surveillance systems. Despite achieving impressive accuracy about 99/55% in detection and 99/21% in classification, the model contains only 0/62 million trainable parameters (625542), making it highly suitable for integration into low-power, real-time environmental monitoring systems.
 

Keywords

Smiley face

References

]۱[ پیکام، علیرضا، شاهبندرزاده، حمید، "اولویت بندی عوامل موثر بر عملکرد پهپادها در صحنه‌ی نبرد ناهمتراز آینده با استفاده از فرآیند تحلیل سلسله مراتبی فازی"، نشریه پدافند غیر عامل، دوره 11، شماره 1، صفحه 51-61، 1399.
https://dor.isc.ac/dor/20.1001.1.20086849.1399.11.1.5.4
]۲[ امیرزاده، مجید، حسینی مرادی، سیدعلی، قبادی، نادر، "تشخیص به‌موقع پرنده‌های هدایت‌پذیر از دور چند بال چرخان با استفاده از الگوریتم YOLOv5 بهینه‌سازی‌شده"، نشریه علوم و فناوری‌های پدافند نوین، دوره 14، شماره 1 - صفحه 11-22، 1402.
https://dor.isc.ac/dor/20.1001.1.26762935.1402.14.1.2.2
]۳[ بهرامی، محمد، اصغری، امیر، بینش مروستی، محمدرضا، انصاریان، سجاد، "ارائه یک روش بهبودیافته تشخیص هواپیمای بدون سرنشین با استفاده از یادگیری عمیق جهت افزایش سرعت تشخیص"، نشریه پدافند الکترونیکی و سایبری، دوره 11، شماره 1، صفحه 81-96، 1402.
https://dor.isc.ac/dor/20.1001.1.23224347.1402.11.1.7.8
[4] Liu, Z., Mao, H., Wu, C. Y., Feichtenhofer, C., Darrell, T., & Xie, S., "A convnet for the 2020s," In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 11976-11986, 2022. https://doi.org/10.1109/CVPR52688.2022.01167
[5] Dong, Y., Wu, F., Zhang, S., Chen, G., Hu, Y., Yano, M., Sun, J., Huang, S., Liu, F., Dai, Q. and Cheng, Z.Q., "Securing the Skies: A Comprehensive Survey on Anti-UAV Methods, Benchmarking, and Future Directions," Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 6659-6673. 2025. https://doi.org/10.48550/arXiv.2504.11967
[6] M. A. Alqodah, M. Tahsin, M. H. Omari, M. M. Matalgah and D. Harrison, "RF-Based Lightweight Machine Learning for Comprehensive Drone Activity Classification," 2024 2nd International Conference on Artificial Intelligence, Blockchain, and Internet of Things (AIBThings), Mt Pleasant, MI, USA, pp. 1-5, 2024. https://doi.org/10.1109/AIBThings63359.2024.10863363
[7] P. Podder, M. Zawodniok and S. Madria, "Deep Learning for UAV Detection and Classification via Radio Frequency Signal Analysis," 2024 25th IEEE International Conference on Mobile Data Management (MDM), Brussels, Belgium, pp. 165-174, 2024. https://doi.org/10.1109/MDM61037.2024.00040
[8] Sazdic-Jotic B, Andric M, Bondzulic B, Simic S, Pokrajac I, "FLEDNet: Enhancing the Drone Classification in the Radio Frequency Domain, " Drones, 9(4), 243, 2025. https://doi.org/10.3390/drones9040243
[9] S. Pant, M. Manning, J. Laliberte, P. Sevigny, S. Rajan and B. Balaji, "Investigating Radar Micro-Doppler Signatures for Drone Payload Detection," 2025 25th International Conference on Digital Signal Processing (DSP), Pylos (Messinia, Southwest Peloponnese), Greece, pp. 1-5, 2025. https://doi.org/10.1109/DSP65409.2025.11075208
[10] J. J. M. de Wit and L. de Martín, "Emerging Trends in Radar: Drone Characterization Using Deep Learning on Micro-Doppler Data," in IEEE Aerospace and Electronic Systems Magazine, vol. 40, no. 6, pp. 48-53, 2025. https://doi.org/10.1109/MAES.2025.3546151
[11] Gong, J., Li, D., Yan, J., & Kong, D., "Comparative Micro-Doppler Signal Detection in L-Band and X-Band Drone Detection Systems, ", International Conference on Autonomous Unmanned Systems, pp. 291-300, 2024. https://doi.org/10.1007/978-981-96-3592-4_30
[12] Islam, S.B., Chowdhury, M.E., Hasan-Zia, M., Kashem, S.B.A., Majid, M.E., Ansaruddin Kunju, A.K., Khandakar, A., Ashraf, A. and Nashbat, M., "VisioDECT: a novel approach to drone detection using CBAM-integrated YOLO and GELAN-E models," Neural Computing and Applications, 1-24, 2025. https://doi.org/10.1007/s00521-025-11448-3
[13] Liu, Z., An, P., Yang, Y., Qiu, S., Liu, Q. and Xu, X., "Vision-based drone detection in complex environments: a survey," Drones, 8(11), p.643, 2024. https://doi.org/10.3390/drones8110643
[14] Seidaliyeva, U., Ilipbayeva, L., Taissariyeva, K., Smailov, N. and Matson, E.T., "Advances and challenges in drone detection and classification techniques: A state-of-the-art review," Sensors, 24(1), p.125, 2023. https://doi.org/10.3390/s24010125
[15] S. Al-Emadi, A. Al-Ali, A. Mohammad and A. Al-Ali, "Audio Based Drone Detection and Identification using Deep Learning," 2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC), Tangier, Morocco, pp. 459-464, 2019. https://doi.org/10.1109/IWCMC.2019.8766732 Available: https://github.com/saraalemadi/DroneAudioDataset
[16] Najafi, J., Mirzakuchaki, S. & Shamaghdari, S., "Autonomous Drone Detection and Classification Using Computer Vision and Prony Algorithm-Based Frequency Feature Extraction, " J Intell Robot Syst 111, 8, 2025. https://doi.org/10.1007/s10846-024-02216-x Available: https://github.com/Jafar-Najafi/Audio-Files
[17] S. Yuan et al., "MMAUD: A Comprehensive Multi-Modal Anti-UAV Dataset for Modern Miniature Drone Threats," 2024 IEEE International Conference on Robotics and Automation (ICRA), Yokohama, Japan, pp. 2745-2751, 2024. https://doi.org/10.1109/ICRA57147.2024.10610957
[18] Alla, I., Olou, H.B., Loscri, V. and Levorato, M., "From sound to sight: Audio-visual fusion and deep learning for drone detection, " Proceedings of the 17th acm conference on security and privacy in wireless and mobile networks, pp. 123-133, 2024. https://doi.org/10.1145/3643833.3656133
[19] Yi, W., Choi, J.W. and Lee, J.W., "Sound-based drone fault classification using multitask learning, " arXiv preprint arXiv:2304.11708, 2023. https://doi.org/10.48550/arXiv.2304.11708 Available: https://zenodo.org/records/7779574
[20] Diao, Y., Zhang, Y., Zhao, G. and Khamis, M., "Drone authentication via acoustic fingerprint," Proceedings of the 38th Annual Computer Security Applications Conference, pp. 658-668, 2022. https://doi.org/10.1145/3564625.3564653 Available: https://researchdata.gla.ac.uk/1348/
[21] Casabianca, P., & Zhang, Y., "Acoustic-based UAV detection using late fusion of deep neural networks," Drones, 5(3), 54, 2021. https://doi.org/10.3390/drones5030054
[22] T. Li, Z. Huang, X. Zhai and S. Wang, "A Lightweight UAV Audio Detection Model Based on Multiscale Feature Fusion," 2023 5th International Academic Exchange Conference on Science and Technology Innovation (IAECST), Guangzhou, China, pp. 1524-1528, 2023. https://doi.org/10.1109/IAECST60924.2023.10503266
[23] S. S. Katta, S. Nandyala, E. K. Viegas and A. AlMahmoud, "Benchmarking Audio-based Deep Learning Models for Detection and Identification of Unmanned Aerial Vehicles," 2022 Workshop on Benchmarking Cyber-Physical Systems and Internet of Things (CPS-IoTBench), Milan, Italy, pp. 7-11, 2022. https://doi.org/10.1109/CPS-IoTBench56135.2022.00008
[24] Wang, M. Y., Chu, Z., Ku, I., Smith, E. C., & Matson, E. T., "A 15-category audio dataset for drones and an audio-based uav classification using machine learning," International Journal of Semantic Computing, 18(02), 257-272, 2024. https://doi.org/10.1142/S1793351X24300048
[25] M. Ohlenbusch, A. Ahrens, C. Rollwage and J. Bitzer, "Robust Drone Detection for Acoustic Monitoring Applications," 2020 28th European Signal Processing Conference (EUSIPCO), Amsterdam, Netherlands, pp. 6-10, 2021. https://doi.org/10.23919/Eusipco47968.2020.9287433
[26] Utebayeva, D., Ilipbayeva, L., & Matson, E. T. "Practical study of recurrent neural networks for efficient real-time drone sound detection: A review," Drones, 7(1), 26, 2022. https://doi.org/10.3390/drones7010026
[27] J. Kim, Q. Zhang, E. T. Matson and M. Y. Wang, "Improving Drone Classification with Audio-Derived Visual Features: A Vision Model Comparison," 2024 Eighth IEEE International Conference on Robotic Computing (IRC), Tokyo, Japan, pp. 41-45, 2024. https://doi.org/10.1109/IRC63610.2024.00013
[28] Downward, B., & Nordby, J., "The AeroSonicDB (YPAD-0523) dataset for acoustic detection and classification of aircraft", arXiv preprint arXiv:2311.06368, 2023. https://doi.org/10.48550/arXiv.2311.06368
Passive Defense
Volume 16, Issue 4 - Serial Number 64
Serial number 64. Winter 2026
February 2026
Pages 121-135

Files

History

  • Receive Date: 26 July 2025
  • Revise Date: 20 September 2025
  • Accept Date: 20 September 2025
  • Publish Date: 21 January 2026

Share

How to cite

Statistics