Fast Independent Vector Extraction by Iterative SINR Maximization

TL;DR

The paper introduces FIVE, a fast algorithm for extracting a single non-Gaussian source from Gaussian noise by iteratively maximizing SINR, demonstrating superior convergence speed and potential for real-time use.

Contribution

FIVE is a novel algorithm that globally minimizes the negative log-likelihood at each iteration, improving speed over existing methods.

Findings

FIVE converges faster than competing algorithms.

FIVE effectively extracts sources in real-time scenarios.

Numerical experiments confirm high performance and robustness.

Abstract

We propose fast independent vector extraction (FIVE), a new algorithm that blindly extracts a single non-Gaussian source from a Gaussian background. The algorithm iteratively computes beamforming weights maximizing the signal-to-interference-and-noise ratio for an approximate noise covariance matrix. We demonstrate that this procedure minimizes the negative log-likelihood of the input data according to a well-defined probabilistic model. The minimization is carried out via the auxiliary function technique whereas, unlike related methods, the auxiliary function is globally minimized at every iteration. Numerical experiments are carried out to assess the performance of FIVE. We find that it is vastly superior to competing methods in terms of convergence speed, and has high potential for real-time applications.