Independent vector analysis -- an introduction for statisticians

Abstract

Blind source separation (BSS), particularly independent component analysis (ICA), has been widely used in various fields of science such as biomedical signal processing to recover latent source signals from the observed mixture. While ICA is typically applied to individual datasets, many real-world applications share underlying sources across datasets. Independent vector analysis (IVA) extends ICA to jointly analyze multiple datasets by exploiting statistical dependencies across them. While various IVA methods have been presented in signal processing literature, the statistical properties of methods remains largely unexplored. This article introduces the IVA model, numerous density models used in IVA, and various classical IVA methods to statistics community highlighting the need for further theoretical developments.

References in corpus (10)

• Pyroomacoustics: A Python package for audio room simulations and array processing algorithms
• Gradient Algorithms for Complex Non-Gaussian Independent Component/Vector Extraction, Question of Convergence
• Independent Vector Analysis: Identification Conditions and Performance Bounds
• Fourth Moments and Independent Component Analysis
• A Unified Bayesian View on Spatially Informed Source Separation and Extraction based on Independent Vector Analysis
• Independent component analysis for tensor-valued data
• Dynamic Independent Component/Vector Analysis: Time-Variant Linear Mixtures Separable by Time-Invariant Beamformers
• The squared symmetric FastICA estimator
• Independent Vector Analysis via Log-Quadratically Penalized Quadratic Minimization
• Independent component analysis for multivariate functional data