Deep Networks for Direction-of-Arrival Estimation in Low SNR

Abstract

In this work, we consider direction-of-arrival (DoA) estimation in the presence of extreme noise using Deep Learning (DL). In particular, we introduce a Convolutional Neural Network (CNN) that is trained from mutli-channel data of the true array manifold matrix and is able to predict angular directions using the sample covariance estimate. We model the problem as a multi-label classification task and train a CNN in the low-SNR regime to predict DoAs across all SNRs. The proposed architecture demonstrates enhanced robustness in the presence of noise, and resilience to a small number of snapshots. Moreover, it is able to resolve angles within the grid resolution. Experimental results demonstrate significant performance gains in the low-SNR regime compared to state-of-the-art methods and without the requirement of any parameter tuning. We relax the assumption that the number of sources is known a priori and present a training method, where the CNN learns to infer the number of sources jointly with the DoAs. Simulation results demonstrate that the proposed CNN can accurately estimate off-grid angles in low SNR, while at the same time the number of sources is successfully inferred for a sufficient number of snapshots. Our robust solution can be applied in several fields, ranging from wireless array sensors to acoustic microphones or sonars.

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Machine learning in acoustics: theory and applications
• Coarrays, MUSIC, and the Cramér Rao Bound
• Multi-Speaker DOA Estimation Using Deep Convolutional Networks Trained with Noise Signals
• Broadband DOA estimation using Convolutional neural networks trained with noise signals
• A discretization-free sparse and parametric approach for linear array signal processing
• Source localization in an ocean waveguide using supervised machine learning

Cited by in corpus (13)

• Ziv-Zakai Bound for DOAs Estimation
• DA-MUSIC: Data-Driven DoA Estimation via Deep Augmented MUSIC Algorithm
• Environment Sensing Considering the Occlusion Effect: A Multi-View Approach
• Super-Resolution Radar Imaging with Sparse Arrays Using a Deep Neural Network Trained with Enhanced Virtual Data
• Audio scene monitoring using redundant ad-hoc microphone array networks
• Subspace Representation Learning for Sparse Linear Arrays to Localize More Sources than Sensors: A Deep Learning Methodology
• Wireless Propagation Parameter Estimation with Convolutional Neural Networks
• A Comparative Study of Invariance-Aware Loss Functions for Deep Learning-based Gridless Direction-of-Arrival Estimation
• Attention-Based Fusion of IQ and FFT Spectrograms with AoA Features for GNSS Jammer Localization
• Measurement-based Evaluation of CNN-based Detection and Estimation for ISAC Systems
• GNSS Jammer Direction Finding in Dynamic Scenarios Using an Inertial-based Multi-Antenna System
• A Supervised Learning Framework for Joint Angle-of-Arrival and Source Number Estimation
• ChainNet: Neural Network-Based Successive Spectral Analysis