Blind Source Separation of Single-Channel Mixtures via Multi-Encoder Autoencoders

📅 2023-08-31
📈 Citations: 1
Influential: 0
📄 PDF
🤖 AI Summary
Addressing the long-standing challenge of single-channel nonlinear blind source separation (BSS), this paper proposes a novel multi-encoder autoencoder framework—the first to introduce a multi-encoder architecture for this task. The method centers on three key components: (i) an encoding mask mechanism that enforces specialization of latent representations into distinct source-specific subspaces; (ii) a sparse mixing loss that regularizes the mixing structure via sparsity-inducing priors; and (iii) a zero-reconstruction loss that ensures orthogonality and interpretability of recovered sources. The model is trained end-to-end to independently estimate and separate constituent sources from their nonlinear mixture. Extensive evaluation on synthetic data and real-world multichannel polysomnography (PSG) recordings—specifically electrocardiogram (ECG) and photoplethysmogram (PPG)-derived respiratory signals—demonstrates substantial performance gains over conventional single-channel BSS approaches. This work establishes a new paradigm for physiological signal disentanglement.
📝 Abstract
The task of blind source separation (BSS) involves separating sources from a mixture without prior knowledge of the sources or the mixing system. Single-channel mixtures and non-linear mixtures are a particularly challenging problem in BSS. In this paper, we propose a novel method for addressing BSS with single-channel non-linear mixtures by leveraging the natural feature subspace specialization ability of multi-encoder autoencoders. 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 sparse mixing loss that encourages sparse remixing of source encodings throughout the decoder and a so-called zero reconstruction loss on the decoder for coherent source estimations. To analyze and evaluate our method, we conduct experiments on a toy dataset, designed to demonstrate this property of feature subspace specialization, and with real-world biosignal recordings from a polysomnography sleep study for extracting respiration from electrocardiogram and photoplethysmography signals.
Problem

Research questions and friction points this paper is trying to address.

Separate sources from single-channel non-linear mixtures blindly
Leverage multi-encoder autoencoders for feature subspace specialization
Develop novel encoding masking and loss functions for source inference
Innovation

Methods, ideas, or system contributions that make the work stand out.

Multi-encoder autoencoders for blind source separation
Encoding masking technique for source signal estimation
Sparse mixing loss for coherent source estimations
🔎 Similar Papers
No similar papers found.
M
Matthew B. Webster
Mellowing Factory Co. Ltd., 708-7 Banpo-dong, Seocho-gu, Seoul, South Korea, 06535
J
Joonnyong Lee
Mellowing Factory Co. Ltd., 708-7 Banpo-dong, Seocho-gu, Seoul, South Korea, 06535