EIHW-MTG DiCOVA 2021 Challenge System Report

TL;DR

This study investigates using spectrogram analysis of cough sounds with deep learning models, including ResNet18 and attention mechanisms, to automatically detect COVID-19, considering gender differences, achieving an AUC of 70.91.

Contribution

It introduces a novel approach combining spectrogram analysis, pre-trained CNNs, and contextual attention for COVID-19 detection from cough sounds.

Findings

ResNet18 with attention achieved 70.91 AUC.

Gender influences COVID-19 detection accuracy.

Spectrogram features contain relevant COVID-19 indicators.

Abstract

This paper aims to automatically detect COVID-19 patients by analysing the acoustic information embedded in coughs. COVID-19 affects the respiratory system, and, consequently, respiratory-related signals have the potential to contain salient information for the task at hand. We focus on analysing the spectrogram representations of coughing samples with the aim to investigate whether COVID-19 alters the frequency content of these signals. Furthermore, this work also assesses the impact of gender in the automatic detection of COVID-19. To extract deep learnt representations of the spectrograms, we compare the performance of a cough-specific, and a Resnet18 pre-trained Convolutional Neural Network (CNN). Additionally, our approach explores the use of contextual attention, so the model can learn to highlight the most relevant deep learnt features extracted by the CNN. We conduct our experiments on the dataset released for the Cough Sound Track of the DiCOVA 2021 Challenge. The best performance on the test set is obtained using the Resnet18 pre-trained CNN with contextual attention, which scored an Area Under the Curve (AUC) of 70.91 at 80% sensitivity.