Svadhyaya system for the Second Diagnosing COVID-19 using Acoustics Challenge 2021
This is an incremental improvement for diagnosing COVID-19 using non-invasive acoustic data in a specific challenge setting.
The paper tackled detecting COVID-19 using acoustic modalities (speech, breathing, cough) in the DiCOVA challenge, achieving blind test AUCs of 86.41, 77.60, and 84.55 for breathing, cough, and speech tracks, respectively, with a fusion AUC of 85.37.
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.