Self-Supervised Blind Source Separation via Multi-Encoder Autoencoders

The task of blind source separation (BSS) involves separating sources from a mixture without prior knowledge of the sources or the mixing system. This is a challenging problem that often requires making restrictive assumptions about both the mixing system and the sources. In this paper, we propose a novel method for addressing BSS of non-linear mixtures by leveraging the natural feature subspace specialization ability of multi-encoder autoencoders with fully self-supervised learning without strong priors. During the training phase, our method unmixes the input into the separate encoding spaces of the multi-encoder network and then remixes these representations within the decoder for a reconstruction of the input. Then to perform source inference, we introduce a novel encoding masking technique whereby masking out all but one of the encodings enables the decoder to estimate a source signal. To this end, we also introduce a so-called pathway separation loss that encourages sparsity between the unmixed encoding spaces throughout the decoder's layers and a so-called zero reconstruction loss on the decoder for coherent source estimations. In order to carefully evaluate our method, we conduct experiments on a toy dataset and with real-world biosignal recordings from a polysomnography sleep study for extracting respiration.