A Cough-based deep learning framework for detecting COVID-19

Abstract

This paper presents a deep learning framework for detecting COVID-19 positive subjects from their cough sounds. In particular, the proposed approach comprises two main steps. In the first step, we generate a feature representing the cough sound by combining an embedding extracted from a pre-trained model and handcrafted features extracted from draw audio recording, referred to as the front-end feature extraction. Then, the combined features are fed into different back-end classification models for detecting COVID-19 positive subjects in the second step. Our experiments on the Track-2 dataset of the Second 2021 DiCOVA Challenge achieved the second top ranking with an AUC score of 81.21 and the top F1 score of 53.21 on a Blind Test set, improving the challenge baseline by 8.43% and 23.4% respectively and showing deployability, robustness and competitiveness with the state-of-the-art systems.

Sound-Dr: Reliable Sound Dataset and Baseline Artificial Intelligence System for Respiratory Illnesses

“…In this paper, the pre-trained model is from both TRILL (Shor et al, 2020) and FRILL (Peplinski, Shor, Joglekar, Garrison, & Patel, 2021), which is recommended for downstream tasks on non-semantic speech signals. Using TRILL to extract features from Cough sounds for detecting COVID-19 has also been proven effective (Hoang, Pham, Ngo, & Nguyen, 2022).…”

A Systematic Review and Analysis on Deep Learning Techniques Used in Diagnosis of Covid-19

“…After applying speech signal processing techniques to pre-process the recorded cough samples, deep convolutional neural networks are employed to extract Mel frequency cepstral coefficient characteristics from the data. Hoang et al [20] In this paper, Light GBM model is used on the Coswara dataset. Light GBM is a gradient boosting framework based on decision trees to increases the efficiency of the model and reduces memory usage.…”