Skip to yearly menu bar Skip to main content


Score-based Source Separation with Applications to Digital Communication Signals

Tejas Jayashankar · Gary C.F. Lee · Alejandro Lancho · Amir Weiss · Yury Polyanskiy · Gregory Wornell

Great Hall & Hall B1+B2 (level 1) #603
[ ] [ Project Page ]
[ Paper [ Poster [ OpenReview
Tue 12 Dec 3:15 p.m. PST — 5:15 p.m. PST

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 $\textit{maximum a posteriori}$ estimation with an $\textit{$\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

Chat is not available.