Home
Scholarly Works
Blind Source Separation in Biomedical Signals...
Preprint

Blind Source Separation in Biomedical Signals Using Variational Methods

Abstract

This study introduces a novel unsupervised approach for separating overlapping heart and lung sounds using variational autoencoders (VAEs). In clinical settings, these sounds often interfere with each other, making manual separation difficult and error-prone. The proposed model learns to encode mixed signals into a structured latent space and reconstructs the individual components using a probabilistic decoder, all without requiring labeled data or prior knowledge of source characteristics. We apply this method to real recordings obtained from a clinical manikin using a digital stethoscope. Results demonstrate distinct latent clusters corresponding to heart and lung sources, as well as accurate reconstructions that preserve key spectral features of the original signals. The approach offers a robust and interpretable solution for blind source separation and has potential applications in portable diagnostic tools and intelligent stethoscope systems.

Authors

Torabi Y; Shirani S; Reilly JP

Publication date

June 23, 2025

DOI

10.48550/arxiv.2506.18281

Preprint server

arXiv
View published work (Non-McMaster Users)

Contact the Experts team