Single-Channel Signal Separation and Deconvolution with Generative Adversarial Networks
It addresses a challenging signal processing problem for applications like audio or image analysis, but appears incremental as it builds on existing GAN and optimization methods.
The paper tackles the problem of single-channel signal separation and deconvolution without prior knowledge of mixing filters, proposing a synthesizing-decomposition approach that uses a GAN for source modeling and optimization for reconstruction, achieving PSNR improvements such as 18.9 dB vs. 15.3 dB in image tasks and 13.2 dB vs. 10.1 dB in separation tasks.
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.