The Use of Audio Signals for Detecting COVID-19: A Systematic Review

Abstract

A systematic review on the topic of automatic detection of COVID-19 using audio signals was performed. A total of 48 papers were obtained after screening 659 records identified in the PubMed, IEEE Xplore, Embase, and Google Scholar databases. The reviewed studies employ a mixture of open-access and self-collected datasets. Because COVID-19 has only recently been investigated, there is a limited amount of available data. Most of the data are crowdsourced, which motivated a detailed study of the various pre-processing techniques used by the reviewed studies. Although 13 of the 48 identified papers show promising results, several have been performed with small-scale datasets (<200). Among those papers, convolutional neural networks and support vector machine algorithms were the best-performing methods. The analysis of the extracted features showed that Mel-frequency cepstral coefficients and zero-crossing rate continue to be the most popular choices. Less common alternatives, such as non-linear features, have also been proven to be effective. The reported values for sensitivity range from 65.0% to 99.8% and those for accuracy from 59.0% to 99.8%.

The smarty4covid dataset and knowledge base as a framework for interpretable physiological audio data analysis

“…However, RT-PCR tests and CT scans suffer from certain limitations such as variable sensitivity and increased turnaround time while requiring highly trained staff, approved laboratories and expensive equipment. The antigen tests constitute an alternative, nevertheless they demonstrate poor sensitivity 5 . An m-health approach able to support affordable, fast, sustainable and effective testing facilitating multiple repetitions to track progression, could contribute in containing the spread and suppressing resurgence 6 .…”

“…An m-health approach able to support affordable, fast, sustainable and effective testing facilitating multiple repetitions to track progression, could contribute in containing the spread and suppressing resurgence 6 . Within this context, the idea of harnessing the power of AI coupled with mobile technologies to implement an easy-to-use and widely accessible COVID-19 detection method, has motivated the application of signal analysis and AI on audio recordings of cough, voice and breath towards the detection of innovative COVID-19 related bio-markers 5 , 7 .…”

Developing a robust technique for denoising and extracting speech and breath sounds in voice recordings from asthmatic patients

“…Out of many important applications, few can be seen in respiratory abnormality detection for ailments, such as bronchitis, asthma, COPD, pertussis and COVID-19 diagnosis. More than 10 databases are publicly available for such research [1]. This type of data includes cough sounds [2, 7 -12], lung sounds [3,5,6], breathing sounds [3,11,12] and voice recordings [4].…”