2025/12/21 by Xuyao Deng, Deng, Xuyao, Yong Dou +3
Computer Science · Engineering · #Aerodynamics and Acoustics in Jet Flows #Computational Engineering #Direction-of-Arrival Estimation Techniques #FOS: Computer and information sciences #Finance #Speech and Audio Processing #and Science (cs.CE)
paper · doi:10.48550/arxiv.2512.18647
openalex publication_date 2025/12/21 · openalex created_date 2025/12/24 · openalex updated_date 2026/07/28
Deep learning-based direction-of-arrival (DoA) estimation has gained increasing popularity. A popular family of DoA estimation algorithms is beamforming methods, which operate by constructing a spatial filter that is applied to array signals. However, these spatial filters obtained by traditional model-driven beamforming algorithms fail under demanding conditions such as coherent sources and a small number of snapshots. In order to obtain a robust spatial filter, this paper proposes BeamformNet-a novel deep learning framework grounded in beamforming principles. Based on the concept of optimal spatial filters, BeamformNet leverages neural networks to approximately obtain the optimal spatial filter via implicit spatial signal focusing and noise suppression, which is then applied to received signals for spatial focusing and noise suppression, thereby enabling accurate DoA estimation. Experimental results on both simulated and real-world speech acoustic source localization data demonstrate that BeamformNet achieves state-of-the-art DoA estimation performance and has better robustness.