Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

COVID-19 Detection System: A Comparative Analysis of System Performance Based on Acoustic Features of Cough Audio Signals

Asmaa Shati, Ghulam Mubashar Hassan, Amitava Datta

TL;DR

This work addresses detecting COVID-19 from cough audio by comparing three acoustic feature families—MFCC, Chroma, and Spectral Contrast—while evaluating two classifiers, MLP and SVM, across six train/test scenarios on COUGHVID and Virufy datasets. MFCC features with an MLP yield the strongest results, achieving AUCs of 0.843 on COUGHVID and 0.953 on Virufy, with combined features offering additional gains in several settings. The study highlights the practical potential of a low-cost, rapid screening pipeline, while noting the influence of data quality and recording conditions on performance and the value of cross-dataset generalization. It also documents a clear advantage of MFCC-based representations for cough analysis and suggests noise filtering and broader validation to enhance robustness.

Abstract

A wide range of respiratory diseases, such as cold and flu, asthma, and COVID-19, affect people's daily lives worldwide. In medical practice, respiratory sounds are widely used in medical services to diagnose various respiratory illnesses and lung disorders. The traditional diagnosis of such sounds requires specialized knowledge, which can be costly and reliant on human expertise. Despite this, recent advancements, such as cough audio recordings, have emerged as a means to automate the detection of respiratory conditions. Therefore, this research aims to explore various acoustic features that enhance the performance of machine learning (ML) models in detecting COVID-19 from cough signals. It investigates the efficacy of three feature extraction techniques, including Mel Frequency Cepstral Coefficients (MFCC), Chroma, and Spectral Contrast features, when applied to two machine learning algorithms, Support Vector Machine (SVM) and Multilayer Perceptron (MLP), and therefore proposes an efficient CovCepNet detection system. The proposed system provides a practical solution and demonstrates state-of-the-art classification performance, with an AUC of 0.843 on the COUGHVID dataset and 0.953 on the Virufy dataset for COVID-19 detection from cough audio signals.

COVID-19 Detection System: A Comparative Analysis of System Performance Based on Acoustic Features of Cough Audio Signals

TL;DR

This work addresses detecting COVID-19 from cough audio by comparing three acoustic feature families—MFCC, Chroma, and Spectral Contrast—while evaluating two classifiers, MLP and SVM, across six train/test scenarios on COUGHVID and Virufy datasets. MFCC features with an MLP yield the strongest results, achieving AUCs of 0.843 on COUGHVID and 0.953 on Virufy, with combined features offering additional gains in several settings. The study highlights the practical potential of a low-cost, rapid screening pipeline, while noting the influence of data quality and recording conditions on performance and the value of cross-dataset generalization. It also documents a clear advantage of MFCC-based representations for cough analysis and suggests noise filtering and broader validation to enhance robustness.

Abstract

A wide range of respiratory diseases, such as cold and flu, asthma, and COVID-19, affect people's daily lives worldwide. In medical practice, respiratory sounds are widely used in medical services to diagnose various respiratory illnesses and lung disorders. The traditional diagnosis of such sounds requires specialized knowledge, which can be costly and reliant on human expertise. Despite this, recent advancements, such as cough audio recordings, have emerged as a means to automate the detection of respiratory conditions. Therefore, this research aims to explore various acoustic features that enhance the performance of machine learning (ML) models in detecting COVID-19 from cough signals. It investigates the efficacy of three feature extraction techniques, including Mel Frequency Cepstral Coefficients (MFCC), Chroma, and Spectral Contrast features, when applied to two machine learning algorithms, Support Vector Machine (SVM) and Multilayer Perceptron (MLP), and therefore proposes an efficient CovCepNet detection system. The proposed system provides a practical solution and demonstrates state-of-the-art classification performance, with an AUC of 0.843 on the COUGHVID dataset and 0.953 on the Virufy dataset for COVID-19 detection from cough audio signals.
Paper Structure (13 sections, 2 equations, 3 figures, 6 tables)

This paper contains 13 sections, 2 equations, 3 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related WORK
  3. Materials and Method
  4. Datasets
  5. Feature Extraction
  6. MFCC Features
  7. Chroma Features
  8. Spectral Contrast Features
  9. Machine learning Models
  10. Results
  11. Ablation Studies
  12. Discussion
  13. Conclusions

Figures (3)

  • Figure 1: (Left) COVID-19 positive cough sample (Right) COVID-19 negative cough sample
  • Figure 2: Block diagram of the experimental procedure
  • Figure 3: MFCC feature extraction process