End-2-End COVID-19 Detection from Breath & Cough Audio
arXiv:2102.08359
Abstract
Our main contributions are as follows: (I) We demonstrate the first attempt to diagnose COVID-19 using end-to-end deep learning from a crowd-sourced dataset of audio samples, achieving ROC-AUC of 0.846; (II) Our model, the COVID-19 Identification ResNet, (CIdeR), has potential for rapid scalability, minimal cost and improving performance as more data becomes available. This could enable regular COVID-19 testing at apopulation scale; (III) We introduce a novel modelling strategy using a custom deep neural network to diagnose COVID-19 from a joint breath and cough representation; (IV) We release our four stratified folds for cross parameter optimisation and validation on a standard public corpus and details on the models for reproducibility and future reference.
arXiv comment5 pages
References in corpus (7)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Exploring Automatic Diagnosis of COVID-19 from Crowdsourced Respiratory Sound Data
- Coswara -- A Database of Breathing, Cough, and Voice Sounds for COVID-19 Diagnosis
- The COUGHVID crowdsourcing dataset: A corpus for the study of large-scale cough analysis algorithms
- Class-Balanced Loss Based on Effective Number of Samples
- Cough Against COVID: Evidence of COVID-19 Signature in Cough Sounds
- COVID-19 Patient Detection from Telephone Quality Speech Data