AUTHOR=Mishra Soumya , Dash Tusar Kanti , Panda Ganapati 

TITLE=Speech phoneme and spectral smearing based non-invasive COVID-19 detection

JOURNAL=Frontiers in Artificial Intelligence

VOLUME=Volume 5 - 2022

YEAR=2023

URL=https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2022.1035805

DOI=10.3389/frai.2022.1035805

ISSN=2624-8212

ABSTRACT=COVID-19 is a deadly viral infection which mainly affects the nasopharyngeal and oropharyngeal
cavity prior to the lung in the human body. Early detection followed by immediate treatment can
potentially reduce lung invasion and decrease fatality. Recently, several COVID-19 detection
methods have been proposed using cough and breath sounds. However, very little work has
been done on the phoneme analysis and smearing of the audio signal in COVID-19 detection.
In this paper, this problem has been considered for the classification of speech samples into
COVID-19 positive and healthy audio samples. Additionally, the grouping of the phonemes based
on reference classification accuracies has been proposed for effective and faster detection of the
disease at a primary stage. The Mel and Gammatone Cepstral Coefficients, and their derivatives
are used as the features for five standard Machine Learning based classifiers. It is observed
that the Generalized Additive Model provides the highest accuracy of 97.22% for the phoneme
grouping ‘/t//r//n//g//l/’. This smearing-based phoneme classification technique can also be used
in the future to classify other speech-related disease detections.