Phonocardiogram Signal Denoising Based on Nonnegative Matrix Factorization and Adaptive Contour Representation Computation

Abstract

This letter introduces a new technique for phonocardiogram (PCG) signal denoising based on nonnegative matrix factorization (NMF) of its spectrogram and adaptive contour representation computation (ACRC) of its short-time Fourier transform (STFT). More precisely, NMFs on PCG and synchronous electrocardiogram spectrograms are first used to filter out high-energy noises from PCG. Then, ACRC is performed on a low-pass filtered version of the STFT of the resulting signal to identify relevant time-frequency components that are subsequently used for signal retrieval. Numerical experiments conducted on a real database of noisy PCG signals, Signal Separation Evaluation Campaign (SiSEC2016), illustrate the superiority of the proposed method over state-of-the-art techniques.