PANACEA cough sound-based diagnosis of COVID-19 for the DiCOVA 2021 Challenge

TL;DR

This paper presents a cough sound-based system for COVID-19 detection developed for the DiCOVA 2021 challenge, achieving a 76.31% AUC, which improves over the baseline, using signal processing and machine learning techniques.

Contribution

The work introduces a novel cough audio analysis system for COVID-19 diagnosis, utilizing TECC features and LightGBM, with significant performance improvement over baseline methods.

Findings

Achieved 76.31% AUC on test set

Improved performance by 10% over baseline

Developed using TECC features and LightGBM

Abstract

The COVID-19 pandemic has led to the saturation of public health services worldwide. In this scenario, the early diagnosis of SARS-Cov-2 infections can help to stop or slow the spread of the virus and to manage the demand upon health services. This is especially important when resources are also being stretched by heightened demand linked to other seasonal diseases, such as the flu. In this context, the organisers of the DiCOVA 2021 challenge have collected a database with the aim of diagnosing COVID-19 through the use of coughing audio samples. This work presents the details of the automatic system for COVID-19 detection from cough recordings presented by team PANACEA. This team consists of researchers from two European academic institutions and one company: EURECOM (France), University of Granada (Spain), and Biometric Vox S.L. (Spain). We developed several systems based on established signal processing and machine learning methods. Our best system employs a Teager energy operator cepstral coefficients (TECCs) based frontend and Light gradient boosting machine (LightGBM) backend. The AUC obtained by this system on the test set is 76.31% which corresponds to a 10% improvement over the official baseline.