Svadhyaya system for the Second Diagnosing COVID-19 using Acoustics Challenge 2021
Audio and Speech Processing
2022-06-14 v1 Machine Learning
Sound
Abstract
This report describes the system used for detecting COVID-19 positives using three different acoustic modalities, namely speech, breathing, and cough in the second DiCOVA challenge. The proposed system is based on the combination of 4 different approaches, each focusing more on one aspect of the problem, and reaches the blind test AUCs of 86.41, 77.60, and 84.55, in the breathing, cough, and speech tracks, respectively, and the AUC of 85.37 in the fusion of these three tracks.
Cite
@article{arxiv.2206.05462,
title = {Svadhyaya system for the Second Diagnosing COVID-19 using Acoustics Challenge 2021},
author = {Deepak Mittal and Amir H. Poorjam and Debottam Dutta and Debarpan Bhattacharya and Zemin Yu and Sriram Ganapathy and Maneesh Singh},
journal= {arXiv preprint arXiv:2206.05462},
year = {2022}
}