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.
翻译:本文介绍了从咳嗽声音中检测COVID-19阳性主题的深层次学习框架,特别是,拟议方法包括两个主要步骤。第一步,我们通过结合从预先训练的模型中提取的嵌入和从抽取录音(称为前端特征提取)中提取的手工制作的特征,产生一个代表咳嗽声的特征。然后,这些综合特征被输入到第二步检测COVID-19阳性主题的不同后端分类模型中。我们在第二个2021年DiCOVA挑战第2轨数据集的实验取得了第二名,ACE分为81.21分,而盲人测试组的F1分为53.21分,挑战基线分别改善了8.43%和23.4%,显示了与最新系统之间的可部署性、稳健性和竞争力。