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.
翻译:基于深度学习的到达方向估计方法日益受到关注。波束形成方法是到达方向估计算法中常用的一类,其通过构建应用于阵列信号的空间滤波器来实现。然而,传统模型驱动的波束形成算法所获得的空间滤波器在相干信源、快拍数较少等苛刻条件下性能不佳。为获得鲁棒的空间滤波器,本文提出BeamformNet——一种基于波束形成原理的新型深度学习框架。基于最优空间滤波器的概念,BeamformNet利用神经网络通过隐式空间信号聚焦与噪声抑制来近似获取最优空间滤波器,随后将其应用于接收信号以实现空间聚焦与噪声抑制,从而完成精确的到达方向估计。在仿真与实际语音声源定位数据上的实验结果表明,BeamformNet实现了最先进的到达方向估计性能,并具有更优的鲁棒性。