DiCOVA Challenge: Dataset, task, and baseline system for COVID-19\n diagnosis using acoustics

2021/03/16 by Ananya Muguli, Lancelot Pinto, Muguli, Ananya +21 · 1 citation
Computer Science · Medicine · #Audio and Speech Processing (eess.AS) #COVID-19 diagnosis using AI #FOS: Computer and information sciences #FOS: Electrical engineering #Music and Audio Processing #Sound (cs.SD) #Speech and Audio Processing #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2103.09148

openalex publication_date 2021/03/16 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28

Abstract

The DiCOVA challenge aims at accelerating research in diagnosing COVID-19\nusing acoustics (DiCOVA), a topic at the intersection of speech and audio\nprocessing, respiratory health diagnosis, and machine learning. This challenge\nis an open call for researchers to analyze a dataset of sound recordings\ncollected from COVID-19 infected and non-COVID-19 individuals for a two-class\nclassification. These recordings were collected via crowdsourcing from multiple\ncountries, through a website application. The challenge features two tracks,\none focusing on cough sounds, and the other on using a collection of breath,\nsustained vowel phonation, and number counting speech recordings. In this\npaper, we introduce the challenge and provide a detailed description of the\ntask, and present a baseline system for the task.\n

Cited by

• Sound Signal Synthesis with Auxiliary Classifier GAN, COVID-19 cough as an example

Related

• The Second DiCOVA Challenge: Dataset and performance analysis for COVID-19 diagnosis using acoustics
• COVID-19 Detection Using Recorded Coughs in the 2021 DiCOVA Challenge
• Towards sound based testing of COVID-19 -- Summary of the first Diagnostics of COVID-19 using Acoustics (DiCOVA) Challenge
• Exploring auditory acoustic features for the diagnosis of the Covid-19
• COVID-19 Diagnosis from Cough Acoustics using ConvNets and Data Augmentation