Automatic Detection of COVID-19 Based on Short-Duration Acoustic Smartphone Speech Analysis

Abstract

Currently, there is an increasing global need for COVID-19 screening to help reduce the rate of infection and at-risk patient workload at hospitals. Smartphone-based screening for COVID-19 along with other respiratory illnesses offers excellent potential due to its rapid-rollout remote platform, user convenience, symptom tracking, comparatively low cost, and prompt result processing timeframe. In particular, speech-based analysis embedded in smartphone app technology can measure physiological effects relevant to COVID-19 screening that are not yet digitally available at scale in the healthcare field. Using a selection of the Sonde Health COVID-19 2020 dataset, this study examines the speech of COVID-19-negative participants exhibiting mild and moderate COVID-19-like symptoms as well as that of COVID-19-positive participants with mild to moderate symptoms. Our study investigates the classification potential of acoustic features (e.g., glottal, prosodic, spectral) from short-duration speech segments (e.g., held vowel, pataka phrase, nasal phrase) for automatic COVID-19 classification using machine learning. Experimental results indicate that certain feature-task combinations can produce COVID-19 classification accuracy of up to 80% as compared with using the all-acoustic feature baseline (68%). Further, with brute-forced n -best feature selection and speech task fusion, automatic COVID-19 classification accuracy of upwards of 82–86% was achieved, depending on whether the COVID-19-negative participant had mild or moderate COVID-19-like symptom severity.

Speaking Corona? Human and Machine Recognition of COVID-19 from Voice

“…Coppock et al [21] reported lower UAR and area under the receiver operating characteristic curve (AUC) scores when distinguishing COVID-19 positive speakers with a cough from COVID-19 negative speakers with a cough. Stasak et al [25] similarly obtained chancelevel results when regarding COVID-19 positive and negative speakers with moderate COVID-19-like symptoms. Conversely, Han et al [22] reported a high rate of asymptomatic patients getting misclassified as healthy speakers.…”

“…Thus, well-founded and not surprisingly, there is also a growing body of research on the automated detection of COVID-19 from voice. Several research groups in the domain of computational paralinguistics have focused their efforts on collecting large 'crowdsourced' datasets (e. g., [17,18,19,20]) using them to create machine learning models (e. g., [21,22,23,24,25,26]). Since voice is a readily available modality and the collection of voice data is non-invasive, voice-based models for COVID-19 detection could serve as valuable screening instruments [27].…”

Deep Learning Based Early Detection Framework for Preliminary Diagnosis of COVID-19 via Onboard Smartphone Sensors

“…For example, Ref. [ 25 ] performs COVID-19 diagnosis using short-duration acoustic smartphone speech analysis. Moreover, authors in [ 26 ] provide a design study of an AI-enabled framework to diagnose COVID-19 using a smartphone.…”

COVID-19 Disease Progression Prediction via Audio Signals: A Longitudinal Study

“…Existing literature has mainly investigated the information content of different audio modalities (e.g. cough, breathing, and voice) [7,8,9,10,11] and the power of various machine learning techniques, especially deep neural networks for COVID-19 detection [12,13,14,15,16,17,18,19]. While success has been witnessed recently in COVID-19 detection from audio signals through machine learning techniques [10], there is still a paucity of work on continuous monitoring of COVID-19 disease progression.…”