Towards Unsupervised Single-Channel Blind Source Separation using Adversarial Pair Unmix-and-Remix
This addresses a long-standing signal processing challenge for applications requiring source separation, but it appears incremental as it adapts adversarial training to an existing task.
The paper tackled the problem of blind single-channel source separation by proposing a novel adversarial method that uses independence of sources to create constraints on pairs of separated sources, achieving good performance validated through experiments on image sources.
Blind single-channel source separation is a long standing signal processing challenge. Many methods were proposed to solve this task utilizing multiple signal priors such as low rank, sparsity, temporal continuity etc. The recent advance of generative adversarial models presented new opportunities in signal regression tasks. The power of adversarial training however has not yet been realized for blind source separation tasks. In this work, we propose a novel method for blind source separation (BSS) using adversarial methods. We rely on the independence of sources for creating adversarial constraints on pairs of approximately separated sources, which ensure good separation. Experiments are carried out on image sources validating the good performance of our approach, and presenting our method as a promising approach for solving BSS for general signals.