Fine-tuning Pre-trained Audio Models for COVID-19 Detection: A Technical Report

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: de Brito, Daniel Oliveira, de Souza, Letícia Gabriella, Gauy, Marcelo Matheus, Finger, Marcelo, Junior, Arnaldo Candido
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918208406028288
author de Brito, Daniel Oliveira
de Souza, Letícia Gabriella
Gauy, Marcelo Matheus
Finger, Marcelo
Junior, Arnaldo Candido
author_facet de Brito, Daniel Oliveira
de Souza, Letícia Gabriella
Gauy, Marcelo Matheus
Finger, Marcelo
Junior, Arnaldo Candido
contents This technical report investigates the performance of pre-trained audio models on COVID-19 detection tasks using established benchmark datasets. We fine-tuned Audio-MAE and three PANN architectures (CNN6, CNN10, CNN14) on the Coswara and COUGHVID datasets, evaluating both intra-dataset and cross-dataset generalization. We implemented a strict demographic stratification by age and gender to prevent models from exploiting spurious correlations between demographic characteristics and COVID-19 status. Intra-dataset results showed moderate performance, with Audio-MAE achieving the strongest result on Coswara (0.82 AUC, 0.76 F1-score), while all models demonstrated limited performance on Coughvid (AUC 0.58-0.63). Cross-dataset evaluation revealed severe generalization failure across all models (AUC 0.43-0.68), with Audio-MAE showing strong performance degradation (F1-score 0.00-0.08). Our experiments demonstrate that demographic balancing, while reducing apparent model performance, provides more realistic assessment of COVID-19 detection capabilities by eliminating demographic leakage - a confounding factor that inflate performance metrics. Additionally, the limited dataset sizes after balancing (1,219-2,160 samples) proved insufficient for deep learning models that typically require substantially larger training sets. These findings highlight fundamental challenges in developing generalizable audio-based COVID-19 detection systems and underscore the importance of rigorous demographic controls for clinically robust model evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2511_14939
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fine-tuning Pre-trained Audio Models for COVID-19 Detection: A Technical Report
de Brito, Daniel Oliveira
de Souza, Letícia Gabriella
Gauy, Marcelo Matheus
Finger, Marcelo
Junior, Arnaldo Candido
Sound
Machine Learning
Audio and Speech Processing
I.2.6; J.3; I.5.4
This technical report investigates the performance of pre-trained audio models on COVID-19 detection tasks using established benchmark datasets. We fine-tuned Audio-MAE and three PANN architectures (CNN6, CNN10, CNN14) on the Coswara and COUGHVID datasets, evaluating both intra-dataset and cross-dataset generalization. We implemented a strict demographic stratification by age and gender to prevent models from exploiting spurious correlations between demographic characteristics and COVID-19 status. Intra-dataset results showed moderate performance, with Audio-MAE achieving the strongest result on Coswara (0.82 AUC, 0.76 F1-score), while all models demonstrated limited performance on Coughvid (AUC 0.58-0.63). Cross-dataset evaluation revealed severe generalization failure across all models (AUC 0.43-0.68), with Audio-MAE showing strong performance degradation (F1-score 0.00-0.08). Our experiments demonstrate that demographic balancing, while reducing apparent model performance, provides more realistic assessment of COVID-19 detection capabilities by eliminating demographic leakage - a confounding factor that inflate performance metrics. Additionally, the limited dataset sizes after balancing (1,219-2,160 samples) proved insufficient for deep learning models that typically require substantially larger training sets. These findings highlight fundamental challenges in developing generalizable audio-based COVID-19 detection systems and underscore the importance of rigorous demographic controls for clinically robust model evaluation.
title Fine-tuning Pre-trained Audio Models for COVID-19 Detection: A Technical Report
topic Sound
Machine Learning
Audio and Speech Processing
I.2.6; J.3; I.5.4
url https://arxiv.org/abs/2511.14939