# Single-Channel Signal Separation and Deconvolution with Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1906.07552 · HTML: https://mlsanity.com/paper/1906.07552/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2019.

## Built on by (most cited first, 9 of 9)

- [Multi-Source Diffusion Models for Simultaneous Music Generation and Separation](https://mlsanity.com/paper/2302.02257/) (2023)
- [Blind Image Decomposition](https://mlsanity.com/paper/2108.11364/) (2021)
- [Simultaneous Music Separation and Generation Using Multi-Track Latent Diffusion Models](https://mlsanity.com/paper/2409.12346/) (2024)
- [Latent Autoregressive Source Separation](https://mlsanity.com/paper/2301.08562/) (2023)
- [MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction](https://mlsanity.com/paper/2505.23305/) (2025)
- [Blind Source Separation of Single-Channel Mixtures via Multi-Encoder Autoencoders](https://mlsanity.com/paper/2309.07138/) (2023)
- [Improving Music Source Separation with Diffusion and Consistency Refinement](https://mlsanity.com/paper/2412.06965/) (2024)
- [Blind stain separation using model-aware generative learning and its applications on fluorescence microscopy images](https://mlsanity.com/paper/2102.06802/) (2021)
- [One to Multiple Mapping Dual Learning: Learning Multiple Sources from One Mixed Signal](https://mlsanity.com/paper/2110.06568/) (2021)

## Abstract (arXiv)

Single-channel signal separation and deconvolution aims to separate and deconvolve individual sources from a single-channel mixture and is a challenging problem in which no prior knowledge of the mixing filters is available. Both individual sources and mixing filters need to be estimated. In addition, a mixture may contain non-stationary noise which is unseen in the training set. We propose a synthesizing-decomposition (S-D) approach to solve the single-channel separation and deconvolution problem. In synthesizing, a generative model for sources is built using a generative adversarial network (GAN). In decomposition, both mixing filters and sources are optimized to minimize the reconstruction error of the mixture. The proposed S-D approach achieves a peak-to-noise-ratio (PSNR) of 18.9 dB and 15.4 dB in image inpainting and completion, outperforming a baseline convolutional neural network PSNR of 15.3 dB and 12.2 dB, respectively and achieves a PSNR of 13.2 dB in source separation together with deconvolution, outperforming a convolutive non-negative matrix factorization (NMF) baseline of 10.1 dB.