ConvNet with MFCC features and data augmentation classifies cough sounds for COVID-19 with 87.07 AUC on the DiCOVA 2021 blind test, outperforming the baseline by 23%.
”DiCOV A Challenge: Dataset, task, and baseline system for COVID-19 diagnosis using acoustics.” arXiv preprint arXiv:2103.09148 (2021)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2021 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
COVID-19 Diagnosis from Cough Acoustics using ConvNets and Data Augmentation
ConvNet with MFCC features and data augmentation classifies cough sounds for COVID-19 with 87.07 AUC on the DiCOVA 2021 blind test, outperforming the baseline by 23%.