Gridless Line Spectral Estimation with Multiple Measurement Vector via Variational Bayesian Inference

TL;DR

This paper introduces MVALSE, a variational Bayesian method for multi snapshot line spectral estimation that automatically estimates model parameters and improves recovery performance over existing methods.

Contribution

The paper develops MVALSE, extending VALSE to multi snapshot scenarios, enabling automatic parameter estimation and improved spectral recovery in array processing.

Findings

MVALSE outperforms state-of-the-art methods in spectral recovery.

MVALSE automatically estimates model order, noise, and weight variances.

Numerical results demonstrate the effectiveness of MVALSE.

Abstract

Line spectral estimation (LSE) from multi snapshot samples is studied utilizing the variational Bayesian methods. Motivated by the recently proposed variational line spectral estimation (VALSE) method for a single snapshot, we develop the multisnapshot VALSE (MVALSE) for multi snapshot scenarios, which is important for array processing. The MVALSE shares the advantages of the VALSE method, such as automatically estimating the model order, noise variance and weight variance, closed-form updates of the posterior probability density function (PDF) of the frequencies. By using multiple snapshots, MVALSE improves the recovery performance and it encodes the prior distribution naturally. Finally, numerical results demonstrate the competitive performance of the MVALSE compared to state-of-the-art methods.