AR-Flow VAE: A Structured Autoregressive Flow Prior Variational Autoencoder for Unsupervised Blind Source Separation

TL;DR

AR-Flow VAE introduces a structured autoregressive flow prior for variational autoencoders, significantly improving unsupervised blind source separation by modeling complex dependencies and non-Gaussian behaviors in latent sources.

Contribution

The paper proposes a novel AR-Flow VAE framework with parameter-adaptive autoregressive flow priors for enhanced blind source separation capabilities.

Findings

Effective separation of sources demonstrated in experiments

Enhanced modeling of complex source dependencies

Framework supports future interpretability studies

Abstract

Blind source separation (BSS) seeks to recover latent source signals from observed mixtures. Variational autoencoders (VAEs) offer a natural perspective for this problem: the latent variables can be interpreted as source components, the encoder can be viewed as a demixing mapping from observations to sources, and the decoder can be regarded as a remixing process from inferred sources back to observations. In this work, we propose AR-Flow VAE, a novel VAE-based framework for BSS in which each latent source is endowed with a parameter-adaptive autoregressive flow prior. This prior significantly enhances the flexibility of latent source modeling, enabling the framework to capture complex non-Gaussian behaviors and structured dependencies, such as temporal correlations, that are difficult to represent with conventional priors. In addition, the structured prior design assigns distinct priors to different latent dimensions, thereby encouraging the latent components to separate into different source signals under heterogeneous prior constraints. Experimental results validate the effectiveness of the proposed architecture for blind source separation. More importantly, this work provides a foundation for future investigations into the identifiability and interpretability of AR-Flow VAE.