# Sounds of COVID-19: exploring realistic performance of audio-based digital testing arXiv: https://arxiv.org/abs/2106.15523 ยท HTML: https://mlsanity.com/paper/2106.15523/ ## Key facts - Cited by 20 papers in the map (data through 14 Oct 2026). - Builds on 15 of its 44 references that are in the map. - First posted on arXiv 29 Jun 2021. ## Builds on (most cited first, 15 of 15) - [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014) - [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017) - [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016) - [Common pitfalls and recommendations for using machine learning to detect and prognosticate for COVID-19 using chest radiographs and CT scans](https://mlsanity.com/paper/2008.06388/) (2020) - [Exploring Automatic Diagnosis of COVID-19 from Crowdsourced Respiratory Sound Data](https://mlsanity.com/paper/2006.05919/) (2020) - [AI4COVID-19: AI Enabled Preliminary Diagnosis for COVID-19 from Cough Samples via an App](https://mlsanity.com/paper/2004.01275/) (2020) - [Exploring Automatic COVID-19 Diagnosis via voice and symptoms from Crowdsourced Data](https://mlsanity.com/paper/2102.05225/) (2021) - [Exploring Self-Supervised Representation Ensembles for COVID-19 Cough Classification](https://mlsanity.com/paper/2105.07566/) (2021) - [An Early Study on Intelligent Analysis of Speech under COVID-19: Severity, Sleep Quality, Fatigue, and Anxiety](https://mlsanity.com/paper/2005.00096/) (2020) - [Detection of COVID-19 through the analysis of vocal fold oscillations](https://mlsanity.com/paper/2010.10707/) (2020) - [COVID-19 Detection in Cough, Breath and Speech using Deep Transfer Learning and Bottleneck Features](https://mlsanity.com/paper/2104.02477/) (2021) - [CovidCTNet: An Open-Source Deep Learning Approach to Identify Covid-19 Using CT Image](https://mlsanity.com/paper/2005.03059/) (2020) - [Hi Sigma, do I have the Coronavirus?: Call for a New Artificial Intelligence Approach to Support Health Care Professionals Dealing With The COVID-19 Pandemic](https://mlsanity.com/paper/2004.06510/) (2020) - [Interpreting glottal flow dynamics for detecting COVID-19 from voice](https://mlsanity.com/paper/2010.16318/) (2020) - [Uncertainty-Aware COVID-19 Detection from Imbalanced Sound Data](https://mlsanity.com/paper/2104.02005/) (2021) ## Built on by (most cited first, 20 of 20) - [Towards Open Respiratory Acoustic Foundation Models: Pretraining and Benchmarking](https://mlsanity.com/paper/2406.16148/) (2024) - [Coswara: A respiratory sounds and symptoms dataset for remote screening of SARS-CoV-2 infection](https://mlsanity.com/paper/2305.12741/) (2023) - [Measuring Cross-Modal Interactions in Multimodal Models](https://mlsanity.com/paper/2412.15828/) (2024) - [Audio-based AI classifiers show no evidence of improved COVID-19 screening over simple symptoms checkers](https://mlsanity.com/paper/2212.08570/) (2022) - [From Personalized Medicine to Population Health: A Survey of mHealth Sensing Techniques](https://mlsanity.com/paper/2107.00948/) (2021) - [Benchmarking Uncertainty Quantification on Biosignal Classification Tasks under Dataset Shift](https://mlsanity.com/paper/2112.09196/) (2021) - [A Summary of the ComParE COVID-19 Challenges](https://mlsanity.com/paper/2202.08981/) (2022) - [Cross-device Federated Learning for Mobile Health Diagnostics: A First Study on COVID-19 Detection](https://mlsanity.com/paper/2303.07067/) (2023) - [A Transfer Learning and Explainable Solution to Detect mpox from Smartphones images](https://mlsanity.com/paper/2305.18489/) (2023) - [Voice EHR: Introducing Multimodal Audio Data for Health](https://mlsanity.com/paper/2404.01620/) (2024) - [Statistical Design and Analysis for Robust Machine Learning: A Case Study from COVID-19](https://mlsanity.com/paper/2212.08571/) (2022) - [On the Impact of Voice Anonymization on Speech Diagnostic Applications: a Case Study on COVID-19 Detection](https://mlsanity.com/paper/2304.02181/) (2023) - [Developing a Multi-variate Prediction Model For COVID-19 From Crowd-sourced Respiratory Voice Data](https://mlsanity.com/paper/2402.07619/) (2024) - [Mitigating Sex Bias in Audio Data-driven COPD and COVID-19 Breathing Pattern Detection Models](https://mlsanity.com/paper/2409.10677/) (2024) - [LeanTTA: A Backpropagation-Free and Stateless Approach to Quantized Test-Time Adaptation on Edge Devices](https://mlsanity.com/paper/2503.15889/) (2025) - [Developing a multi-variate prediction model for the detection of COVID-19 from Crowd-sourced Respiratory Voice Data](https://mlsanity.com/paper/2209.03727/) (2022) - [VoCopilot: Voice-Activated Tracking of Everyday Interactions](https://mlsanity.com/paper/2312.10265/) (2023) - [An AI-enabled Bias-Free Respiratory Disease Diagnosis Model using Cough Audio: A Case Study for COVID-19](https://mlsanity.com/paper/2401.02996/) (2024) - [Sustaining model performance for covid-19 detection from dynamic audio data: Development and evaluation of a comprehensive drift-adaptive framework](https://mlsanity.com/paper/2409.19300/) (2024) - [CoughViT: A Self-Supervised Vision Transformer for Cough Audio Representation Learning](https://mlsanity.com/paper/2508.03764/) (2025) ## Abstract (arXiv) Researchers have been battling with the question of how we can identify Coronavirus disease (COVID-19) cases efficiently, affordably and at scale. Recent work has shown how audio based approaches, which collect respiratory audio data (cough, breathing and voice) can be used for testing, however there is a lack of exploration of how biases and methodological decisions impact these tools' performance in practice. In this paper, we explore the realistic performance of audio-based digital testing of COVID-19. To investigate this, we collected a large crowdsourced respiratory audio dataset through a mobile app, alongside recent COVID-19 test result and symptoms intended as a ground truth. Within the collected dataset, we selected 5,240 samples from 2,478 participants and split them into different participant-independent sets for model development and validation. Among these, we controlled for potential confounding factors (such as demographics and language). The unbiased model takes features extracted from breathing, coughs, and voice signals as predictors and yields an AUC-ROC of 0.71 (95% CI: 0.65-0.77). We further explore different unbalanced distributions to show how biases and participant splits affect performance. Finally, we discuss how the realistic model presented could be integrated in clinical practice to realize continuous, ubiquitous, sustainable and affordable testing at population scale.