We introduce a U-net model for 360° acoustic source localization formulated as a spherical semantic segmentation task. Rather than regressing discrete direction-of-arrival (DoA) angles, our model segments beamformed audio maps (azimuth and elevation) into regions of active sound presence. Using delay-and-sum (DAS) beamforming on a custom 24-microphone array, we generate signals aligned with drone GPS telemetry to create binary supervision masks. A modified U-Net, trained on frequency-domain representations of these maps, learns to identify spatially distributed source regions while addressing class imbalance via the Tversky loss. Because the network operates on beamformed energy maps, the approach is inherently array-independent and can adapt to different microphone configurations without retraining from scratch. The segmentation outputs are post-processed by computing centroids over activated regions, enabling robust DoA estimates. Our dataset includes real-world open-field recordings of a DJI Air 3 drone, synchronized with 360° video and flight logs across multiple dates and locations. Experimental results show that U-net generalizes across environments, providing improved angular precision, offering a new paradigm for dense spatial audio understanding beyond traditional Sound Source Localization (SSL).

翻译：我们提出了一种用于360°声源定位的U-Net模型，该模型被形式化为球面语义分割任务。该模型不直接回归离散的到达方向（DoA）角度，而是将波束形成的音频图（方位角和仰角）分割为活跃声源存在区域。通过定制24麦克风阵列的延时求和（DAS）波束形成，我们生成与无人机GPS遥测数据对齐的信号，从而构建二值监督掩码。通过在频域表示上训练改进的U-Net，模型能够学习识别空间分布声源区域，并利用Tversky损失函数缓解类别不平衡问题。由于网络基于波束形成能量图，该方法本质上与阵列结构无关，可无需从头重新训练即可适应不同麦克风配置。通过对分割结果中的激活区域计算质心进行后处理，可获得稳健的DoA估计。我们的数据集包含真实场景下DJI Air 3无人机的开阔场地录音，并与多日期、多地点的360°视频和飞行日志同步。实验结果表明，U-Net能够跨环境泛化，提供更优的角度精度，为超越传统声源定位（SSL）的密集空间音频理解开辟了新范式。