# Audio feature ranking for sound-based COVID-19 patient detection

arXiv: https://arxiv.org/abs/2104.07128 · HTML: https://mlsanity.com/paper/2104.07128/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 27 references that are in the map.
- First posted on arXiv 14 Apr 2021.

## Builds on (most cited first, 4 of 4)

- [Exploring Automatic Diagnosis of COVID-19 from Crowdsourced Respiratory Sound Data](https://mlsanity.com/paper/2006.05919/) (2020)
- [Coswara -- A Database of Breathing, Cough, and Voice Sounds for COVID-19 Diagnosis](https://mlsanity.com/paper/2005.10548/) (2020)
- [DiCOVA Challenge: Dataset, task, and baseline system for COVID-19 diagnosis using acoustics](https://mlsanity.com/paper/2103.09148/) (2021)
- [Feature Learning for Chord Recognition: The Deep Chroma Extractor](https://mlsanity.com/paper/1612.05065/) (2016)

## Built on by (most cited first, 3 of 3)

- [A Closer Look at AUROC and AUPRC under Class Imbalance](https://mlsanity.com/paper/2401.06091/) (2024)
- [A novel Deep Learning approach for one-step Conformal Prediction approximation](https://mlsanity.com/paper/2207.12377/) (2022)
- [Fused Audio Instance and Representation for Respiratory Disease Detection](https://mlsanity.com/paper/2204.10581/) (2022)

## Abstract (arXiv)

Audio classification using breath and cough samples has recently emerged as a low-cost, non-invasive, and accessible COVID-19 screening method. However, a comprehensive survey shows that no application has been approved for official use at the time of writing, due to the stringent reliability and accuracy requirements of the critical healthcare setting. To support the development of Machine Learning classification models, we performed an extensive comparative investigation and ranking of 15 audio features, including less well-known ones. The results were verified on two independent COVID-19 sound datasets. By using the identified top-performing features, we have increased COVID-19 classification accuracy by up to 17% on the Cambridge dataset and up to 10% on the Coswara dataset compared to the original baseline accuracies without our feature ranking.