An incremental algorithm based on multichannel non-negative matrix partial co-factorization for ambient denoising in auscultation

Abstract

One of the major current limitations in the diagnosis derived from auscultation remains the ambient noise surrounding the subject, which prevents successful auscultation. Therefore, it is essential to develop robust signal processing algorithms that can extract relevant clinical information from auscultated recordings analyzing in depth the acoustic environment in order to help the decision-making process made by physicians. The aim of this study is to implement a method to remove ambient noise in biomedical sounds captured in auscultation. We propose an incremental approach based on multichannel non-negative matrix partial co-factorization (NMPCF) for ambient denoising focusing on high noisy environment with a Signal-to-Noise Ratio (SNR) 6 5 dB. The first contribution applies NMPCF assuming that ambient noise can be modelled as repetitive sound events simultaneously found in two single-channel inputs captured by means of different recording devices. The second contribution proposes an incremental algorithm, based on the previous multichannel NMPCF, that refines the estimated biomedical spectrogram throughout a set of incremental stages by eliminating most of the ambient noise that was not removed in the previous stage at the expense of preserving most of the biomedical spectral content. The ambient denoising performance of the proposed method, compared to some of the most relevant state-of-the-art methods, has been evaluated using a set of recordings composed of biomedical sounds mixed with ambient noise that typically surrounds a medical consultation room to simulate high noisy environments with a SNR from -20 dB to -5 dB. In order to analyse the drop in denoising performance of the evaluated methods when the effect of the propagation of the patient’s body material and the acoustics of the room is considered, results have been obtained with and without taking these effects into account. Experimental results report that: (i) the performance drop suffered by the proposed method is lower compared to MSS and NLMS when considering the effect of the propagation of the patient’s body material and the acoustics of the room active; (ii) unlike what happens with MSS and NLMS, the proposed method shows a stable trend of the average SDR and SIR results regardless of the type of ambient noise and the SNR level evaluated; and (iii) a remarkable advantage of the proposed method is the high robustness of the acoustic quality of the estimated biomedical sounds when the two single-channel inputs suffer from a delay between them.