COVID-19 Detection using Audio Spectral Features and Machine Learning

The project uses spectral features from audio spectrograms coughing and breathing sounds and uses machine learning to detect COVID-19 symptoms. Various machine learning algorithms are explored including convolutional neural networks (CNNs), convolutional recurrent neural networks (CRNNs), and graph convolutional recurrent neural networks (GCRNNs). These algorithms are implemented in Python and profiled in terms of performance and complexity. The target platform will be a mobile device.

PI: Andreas Spanias

Researcher Associates: Michael Esposito, Sunil Rao, Vivek Narayanaswamy

Sponsor:  NSF I/UCRC Grant

Abstract: Click here to view

Poster: Click here to view