TSNetIQ: High-Resolution DOA Estimation of UAVs Using Microphone Arrays
Source abstract
Abstract
With the rapid development of unmanned aerial vehicle (UAV) technology and the rise of the low-altitude economy, the accurate tracking of UAVs has become a critical challenge. This paper considers a deep learning-based localization scheme that combines microphone arrays for audio source reception. The microphone array is utilized to capture sound source reception from various angles. The proposed TSNetIQ combines elaborately designed Transformer and convolutional neural networks (CNN) modules, and the raw in-phase (I) and quadrature (Q) components of the audio signals are used as input data. Hence, the direction of arrival (DOA) estimation is treated as a regression problem. Experiments are conducted to evaluate the proposed method under different signal-to-noise ratios (SNRs), sampling frequencies, and array configurations. The results demonstrate that TSNetIQ can effectively estimate the direction of the sound source, outperforming conventional architectures trained with the same dataset. This study offers superior accuracy and robustness for real-time sound source localization in UAV applications under dynamic scenarios.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Speech and Audio Processing · Direction-of-Arrival Estimation Techniques · Indoor and Outdoor Localization Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Communications and Information Engineering, University of Posts and Telecommunications, Nanjing 210003, China
Tongding Interconnection Information Company, Ltd., Suzhou 215233, China
Funding
Natural Science Foundation of the Jiangsu Higher Education Institutions of China · Key Research and Development Program of Wuhan
References (35)
Show source-provided references
1. Complex-Valued Convolutional Neural Networks Design and its Application on UAV DOA Estimation in Urban Environments10.23919/JCIN.2020.9130429 ↗
2. SLAM-Based Joint Calibration of Multiple Asynchronous Microphone Arrays and Sound Source Localization10.1109/TRO.2024.3410456 ↗
3. A Closed-Form DOA Estimator Using Spherical Microphone Arrays in the Presence of Interference10.1109/LSP.2024.3422789 ↗
4. Lee, S.Y., Chang, J., and Lee, S. (2022). Deep Learning-Enabled High-Resolution and Fast Sound Source Localization in Spherical Microphone Array System. IEEE Trans. Instrum. Meas., 71.10.1109/TIM.2022.3161693 ↗
5. Maximum likelihood methods for direction-of-arrival estimation10.1109/29.57542 ↗
6. Closed-Form DOA Estimation Using First-Order Differential Microphone Arrays via Joint Temporal-Spectral-Spatial Processing10.1109/JSEN.2016.2641449 ↗
7. Source localization and beamforming10.1109/79.985676 ↗
8. Lu, D., Liu, Y., Huang, W., and Xi, X. (2020, January 2–6). Accurate Fault Location in AC/DC Hybrid Line Corridors Based on Eigenvalue Decomposition. Proceedings of the 2020 IEEE Power & Energy Society General Meeting (PESGM), Montreal, QC, Canada.10.1109/PESGM41954.2020.9281903 ↗
9. Multiple emitter location and signal parameter estimation10.1109/TAP.1986.1143830 ↗
10. SAGE-based algorithm for DOA estimation and array calibration in the presence of sensor location errors10.21629/JSEE.2019.06.03 ↗
11. Downlink Performance of Massive-MIMO Systems Using EVD-Based Channel Estimation10.1109/TVT.2016.2590943 ↗
12. DOA Estimation Based on Pseudo-Noise Subspace for Relocating Enhanced Nested Array10.1109/LSP.2022.3199149 ↗
13. Veerendra, D., Balamurugan, K.S., Villagómez-Galindo, K.S., Khandare, M., Patil, A., and Jaganathan, M. (2023). Optimizing Sensor Array DOA Estimation with the Manifold Reconstruction Unitary ESPRIT Algorithm. IEEE Sens. Lett., 7.10.1109/LSENS.2023.3327568 ↗
14. ESPRIT-estimation of signal parameters via rotational invariance techniques10.1109/29.32276 ↗
15. A Review of the State of the Art and Future Challenges of Deep Learning-Based Beamforming10.1109/ACCESS.2022.3195299 ↗
16. Chen, F., Yang, D., Mo, S., Huang, X., Wang, M., Zhu, Z., and Li, Y. (2024). A Method for Estimating the Direction of Arrival Without Knowing the Source Number Using Acoustic Vector Sensor Arrays. IEEE Trans. Geosci. Remote Sens., 62.10.1109/TGRS.2024.3387104 ↗
17. DOA Estimation via Sparse Signal Recovery in 4-D Linear Antenna Arrays with Optimized Time Sequences10.1109/TVT.2019.2955083 ↗
18. Iterative Sparse Asymptotic Minimum Variance Based Approaches for Array Processing10.1109/TSP.2012.2231676 ↗
19. The, Q.T., Huy, N.B., and Anh, P.T. (2023, January 22). A method for reducing speech distortion in minimum variance distortionless response beamformer. Proceedings of the 2023 Seminar on Signal Processing, Saint Petersburg, Russia.10.1109/IEEECONF60473.2023.10366165 ↗
20. Kase, Y., Nishimura, T., Ohgane, T., Ogawa, Y., Kitayama, D., and Kishiyama, Y. (2019, January 24–27). Performance analysis of DOA estimation of two targets using deep learning. Proceedings of the 2019 22nd International Symposium on Wireless Personal Multimedia Communications (WPMC), Lisbon, Portugal.10.1109/WPMC48795.2019.9096165 ↗
21. A novel three-dimensional direction-of-arrival estimation approach using a deep convolutional neural network10.1109/OJVT.2024.3390833 ↗
22. Dual class token vision transformer for direction of arrival estimation in low SNR10.1109/LSP.2023.3342628 ↗
23. Kase, Y., Nishimura, T., Ohgane, T., Ogawa, Y., Kitayama, D., and Kishiyama, Y. (2018, January 15–16). DOA estimation of two targets with deep learning. Proceedings of the 2018 15th Workshop on Positioning, Navigation and Communications (WPNC), Bremen, Germany.10.1109/WPNC.2018.8555814 ↗
24. Deep convolution network for direction of arrival estimation with sparse prior10.1109/LSP.2019.2945115 ↗
25. Elbir, A.M. (2020). DeepMUSIC: Multiple signal classification via deep learning. IEEE Sens. Lett., 4.10.1109/LSENS.2020.2980384 ↗
26. Fast and Precise Positioning in PCBs Using Deep Neural Network Regression10.1109/TIM.2019.2957866 ↗
27. Deep networks for direction-of-arrival estimation in low SNR10.1109/TSP.2021.3089927 ↗
28. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., and Polosukhin, I. (2017, January 4–9). Attention is all you need. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA.
29. Hybrid Multi-Class Token Vision Transformer Convolutional Network for DOA Estimation10.1109/LSP.2025.3573949 ↗
30. A Spatiotemporal Information-Driven Cross-Attention Model with Sparse Representation for GNSS NLOS Signal Classification10.1109/JIOT.2024.3423016 ↗
31. Deep learning-based DOA estimation10.1109/TCCN.2024.3360527 ↗
32. Enhancing Single Object Tracking with a Hybrid Approach: Temporal Convolutional Networks, Attention Mechanisms, and Spatial–Temporal Memory10.1109/ACCESS.2023.3330644 ↗
33. Liu, F., Yao, L., Zhang, C., Wu, T., Zhang, X., Jiang, X., and Zhou, J. (2025). Boost UAV-Based Object Detection via Scale-Invariant Feature Disentanglement and Adversarial Learning. IEEE Trans. Geosci. Remote Sens., 63.10.1109/TGRS.2025.3564261 ↗
34. MS-HNN: Multi-Scale Hierarchical Neural Network with Squeeze-and-Excitation Block for Neonatal Sleep Staging Using Single-Channel EEG10.1109/TNSRE.2023.3266876 ↗
35. Scheibler, R., Bezzam, E., and Dokmanić, I. (2018, January 15–20). Pyroomacoustics: A Python package for audio room simulation and array processing algorithms. Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada.10.1109/ICASSP.2018.8461310 ↗