Score-based Source Separation with Applications to Digital Communication Signals

TL;DR

This paper introduces a diffusion-based source separation method using statistical priors, significantly reducing bit error rates in RF signal applications and extending score distillation sampling techniques.

Contribution

It presents a novel diffusion-based approach for source separation that leverages independent source priors and applies to RF signals, improving accuracy over existing methods.

Findings

Achieves 95% reduction in bit error rate compared to classical methods.

Demonstrates solutions approach the modes of discrete distributions.

Extends score distillation sampling to multi-source separation.

Abstract

We propose a new method for separating superimposed sources using diffusion-based generative models. Our method relies only on separately trained statistical priors of independent sources to establish a new objective function guided by maximum a posteriori estimation with an $\alpha$-posterior, across multiple levels of Gaussian smoothing. Motivated by applications in radio-frequency (RF) systems, we are interested in sources with underlying discrete nature and the recovery of encoded bits from a signal of interest, as measured by the bit error rate (BER). Experimental results with RF mixtures demonstrate that our method results in a BER reduction of 95% over classical and existing learning-based methods. Our analysis demonstrates that our proposed method yields solutions that asymptotically approach the modes of an underlying discrete distribution. Furthermore, our method can be viewed as a multi-source extension to the recently proposed score distillation sampling scheme, shedding additional light on its use beyond conditional sampling. The project webpage is available at https://alpha-rgs.github.io