Joint-Scnn: Joint Spiking Convolution Network for Direction of Arrival Estimation

Direction of arrival (DOA) refers to finding direction information of propagating waves from the received antennas equipped with several sensors. Recently, we have witnessed an enrichment of source data prompting us to design more robust DOA estimator, where artificial neural network (ANN)-based DOA estimators have shown their superior performance as compared to the traditional subspace-based DOA estimation methods. However, these data-driven DOA estimation methods tend to rely on parameters that are computationally intensive for efficient processing/running with the limitation of hardware resources. Thus, we propose an event-driven spiking neural network (SNN) model, namely, Joint-Scnn, for DOA in the presence of various imperfections, which consists of ANN-based and SNN-based modules with weights sharing. The former not only contributes to assist sparse SNN-based module to learn latent information, but also enhances its robustness via self-learning. The superior estimation performance and lower power consumption have been verified via experimental results. The success of Joint-Scnn is partially attributed to the teacher-student tandem learning scheme.