Large Language Model-based Nonnegative Matrix Factorization For Cardiorespiratory Sound Separation

2025/02/09 by Yasaman Torabi, Torabi, Yasaman, Shahram Shirani +3 · 5 citations
Computer Science · Medicine · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Phonocardiography and Auscultation Techniques #Signal Processing (eess.SP) #Sound (cs.SD) #Speech Recognition and Synthesis #Voice and Speech Disorders #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2502.05757

openalex publication_date 2025/02/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This study represents the first integration of large language models (LLMs) with non-negative matrix factorization (NMF), marking a novel advancement in the source separation field. The LLM is employed in two unique ways: enhancing the separation results by providing detailed insights for disease prediction and operating in a feedback loop to optimize a fundamental frequency penalty added to the NMF cost function. We tested the algorithm on two datasets: 100 synthesized mixtures of real measurements, and 210 recordings of heart and lung sounds from a clinical manikin including both individual and mixed sounds, captured using a digital stethoscope. The approach consistently outperformed existing methods, demonstrating its potential to significantly enhance medical sound analysis for disease diagnostics.

Cited by

• QuPCG: Quantum Convolutional Neural Network for Detecting Abnormal Patterns in PCG Signals
• GUSL-Dehaze: A Green U-Shaped Learning Approach to Image Dehazing
• Chem-NMF: Multi-layer α-divergence Non-Negative Matrix Factorization for Cardiorespiratory Disease Clustering, with Improved Convergence Inspired by Chemical Catalysts and Rigorous Asymptotic Analysis
• From Filters to VLMs: Benchmarking Defogging Methods through Object Detection and Segmentation Performance
• Large Language Models and Non-Negative Matrix Factorization for Bioacoustic Signal Decomposition

Related

• Large Language Models and Non-Negative Matrix Factorization for Bioacoustic Signal Decomposition
• A New Non-Negative Matrix Factorization Approach for Blind Source Separation of Cardiovascular and Respiratory Sound Based on the Periodicity of Heart and Lung Function
• Assessing the Utility of Audio Foundation Models for Heart and Respiratory Sound Analysis
• Exploring Finetuned Audio-LLM on Heart Murmur Features
• Manikin-Recorded Cardiopulmonary Sounds Dataset Using Digital Stethoscope