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

arXiv: https://arxiv.org/abs/2309.07138 · HTML: https://mlsanity.com/paper/2309.07138/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 101 references that are in the map.
- First posted on arXiv 31 Aug 2023.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation](https://mlsanity.com/paper/1809.07454/) (2018)
- [Deep clustering: Discriminative embeddings for segmentation and separation](https://mlsanity.com/paper/1508.04306/) (2015)
- [Attention is All You Need in Speech Separation](https://mlsanity.com/paper/2010.13154/) (2020)
- [Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation](https://mlsanity.com/paper/1910.06379/) (2019)
- [Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation](https://mlsanity.com/paper/1806.03185/) (2018)
- [TasNet: time-domain audio separation network for real-time, single-channel speech separation](https://mlsanity.com/paper/1711.00541/) (2017)
- ["Double-DIP": Unsupervised Image Decomposition via Coupled Deep-Image-Priors](https://mlsanity.com/paper/1812.00467/) (2018)
- [Context-Aware Neural Machine Translation Learns Anaphora Resolution](https://mlsanity.com/paper/1805.10163/) (2018)
- [Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation](https://mlsanity.com/paper/2007.13975/) (2020)
- [Source Separation with Deep Generative Priors](https://mlsanity.com/paper/2002.07942/) (2020)
- [Learning Independent Features with Adversarial Nets for Non-linear ICA](https://mlsanity.com/paper/1710.05050/) (2017)
- [Why Self-Attention? A Targeted Evaluation of Neural Machine Translation Architectures](https://mlsanity.com/paper/1808.08946/) (2018)
- [MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions](https://mlsanity.com/paper/2302.11824/) (2023)
- [Deep attractor network for single-microphone speaker separation](https://mlsanity.com/paper/1611.08930/) (2016)
- [Meta-learning Extractors for Music Source Separation](https://mlsanity.com/paper/2002.07016/) (2020)
- [Adversarial Semi-Supervised Audio Source Separation applied to Singing Voice Extraction](https://mlsanity.com/paper/1711.00048/) (2017)
- [An End-to-End and Accurate PPG-based Respiratory Rate Estimation Approach Using Cycle Generative Adversarial Networks](https://mlsanity.com/paper/2105.00594/) (2021)
- [Single-Channel Signal Separation and Deconvolution with Generative Adversarial Networks](https://mlsanity.com/paper/1906.07552/) (2019)
- [RespNet: A deep learning model for extraction of respiration from photoplethysmogram](https://mlsanity.com/paper/1902.04236/) (2019)
- [ProtoCaps: A Fast and Non-Iterative Capsule Network Routing Method](https://mlsanity.com/paper/2307.09944/) (2023)
- [CASS: Cross Adversarial Source Separation via Autoencoder](https://mlsanity.com/paper/1905.09877/) (2019)
- [Towards Unsupervised Single-Channel Blind Source Separation using Adversarial Pair Unmix-and-Remix](https://mlsanity.com/paper/1812.07504/) (2018)
- [Blind Source Separation: Fundamentals and Recent Advances (A Tutorial Overview Presented at SBrT-2001)](https://mlsanity.com/paper/1603.03089/) (2016)

## Built on by (most cited first, 1 of 1)

- [Self-Supervised Autoencoder Network for Robust Heart Rate Extraction from Noisy Photoplethysmogram: Applying Blind Source Separation to Biosignal Analysis](https://mlsanity.com/paper/2504.09132/) (2025)

## Abstract (arXiv)

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.