One to Multiple Mapping Dual Learning: Learning Multiple Sources from One Mixed Signal

TL;DR

This paper introduces PDualGAN, a novel dual generative adversarial network that effectively separates multiple sources from a single mixed signal, demonstrating superior performance across various models and datasets.

Contribution

The paper proposes a new parallel dual GAN framework for one-to-multiple source separation, extending beyond two sources and improving generalization in SCBSS tasks.

Findings

Achieves high PSNR and correlation in source separation

Outperforms existing state-of-the-art algorithms

Effective across different mixed models and datasets

Abstract

Single channel blind source separation (SCBSS) refers to separate multiple sources from a mixed signal collected by a single sensor. The existing methods for SCBSS mainly focus on separating two sources and have weak generalization performance. To address these problems, an algorithm is proposed in this paper to separate multiple sources from a mixture by designing a parallel dual generative adversarial Network (PDualGAN) that can build the relationship between a mixture and the corresponding multiple sources to realize one-to-multiple cross-domain mapping. This algorithm can be applied to any mixed model such as linear instantaneous mixed model and convolutional mixed model. Besides, one-to-multiple datasets are created which including the mixtures and corresponding sources for this study. The experiment was carried out on four different datasets and tested with signals mixed in different proportions. Experimental results show that the proposed algorithm can achieve high performance in peak signal-to-noise ratio (PSNR) and correlation, which outperforms state-of-the-art algorithms.