Exploiting Temporal Structures of Cyclostationary Signals for Data-Driven Single-Channel Source Separation

Gary C.F. Lee, Amir Weiss, Alejandro Lancho, Jennifer Tang, Yuheng Bu, Yury Polyanskiy, Gregory W. Wornell

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We study the problem of single-channel source separation (SCSS), and focus on cyclostationary signals, which are particularly suitable in a variety of application domains. Unlike classical SCSS approaches, we consider a setting where only examples of the sources are available rather than their models, inspiring a data-driven approach. For source models with underlying cyclostationary Gaussian constituents, we establish a lower bound on the attainable mean-square-error (MSE) for any separation method, model-based or data-driven. Our analysis further reveals the operation for optimal separation and the associated implementation challenges. As a computationally attractive alternative, we propose a deep learning approach using a U-Net architecture, which is competitive with the minimum MSE estimator. We demonstrate in simulation that, with suitable domain-informed architectural choices, our U-Net method can approach the optimal performance with substantially reduced computational burden.

Original languageEnglish
Title of host publication2022 IEEE 32nd International Workshop on Machine Learning for Signal Processing, MLSP 2022
PublisherIEEE Computer Society
ISBN (Electronic)9781665485470
DOIs
StatePublished - 2022
Externally publishedYes
Event32nd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2022 - Xi'an, China
Duration: 22 Aug 202225 Aug 2022

Publication series

NameIEEE International Workshop on Machine Learning for Signal Processing, MLSP
Volume2022-August

Conference

Conference32nd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2022
Country/TerritoryChina
CityXi'an
Period22/08/2225/08/22

Keywords

  • cyclostationary signal processing
  • deep neural network
  • Source separation
  • supervised learning

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction
  • Signal Processing

Cite this