On the pragmatism of using binary classifiers over data intensive neural network classifiers for detection of COVID-19 from voice

TL;DR

This paper demonstrates that simple binary classifiers using standard features outperform complex neural networks in detecting COVID-19 from voice, offering a more accurate, interpretable, and computationally efficient solution suitable for local device deployment.

Contribution

It shows that standard features and binary classifiers are sufficient for COVID-19 voice detection, challenging the need for complex neural network models.

Findings

Binary classifiers outperform neural networks in accuracy.

Standard features are effective for COVID-19 voice detection.

Method is computationally efficient and suitable for local devices.

Abstract

Lately, there has been a global effort by multiple research groups to detect COVID-19 from voice. Different researchers use different kinds of information from the voice signal to achieve this. Various types of phonated sounds and the sound of cough and breath have all been used with varying degree of success in automated voice-based COVID-19 detection apps. In this paper, we show that detecting COVID-19 from voice does not require custom-made non-standard features or complicated neural network classifiers rather it can be successfully done with just standard features and simple binary classifiers. In fact, we show that the latter is not only more accurate and interpretable but also more computationally efficient in that they can be run locally on small devices. We demonstrate this on a human-curated dataset of over 1000 subjects, collected and calibrated in clinical settings.