CovNet

A Transfer Learning Framework for Automatic COVID-19 Detection From Crowd-Sourced Cough Sounds

authored by: Yi Chang, Xin Jing, Zhao Ren, Björn W. Schuller
Abstract: Since the COronaVIrus Disease 2019 (COVID-19) outbreak, developing a digital diagnostic tool to detect COVID-19 from respiratory sounds with computer audition has become an essential topic due to its advantages of being swift, low-cost, and eco-friendly. However, prior studies mainly focused on small-scale COVID-19 datasets. To build a robust model, the large-scale multi-sound FluSense dataset is utilised to help detect COVID-19 from cough sounds in this study. Due to the gap between FluSense and the COVID-19-related datasets consisting of cough only, the transfer learning framework (namely CovNet) is proposed and applied rather than simply augmenting the training data with FluSense. The CovNet contains (i) a parameter transferring strategy and (ii) an embedding incorporation strategy. Specifically, to validate the CovNet's effectiveness, it is used to transfer knowledge from FluSense to COUGHVID, a large-scale cough sound database of COVID-19 negative and COVID-19 positive individuals. The trained model on FluSense and COUGHVID is further applied under the CovNet to another two small-scale cough datasets for COVID-19 detection, the COVID-19 cough sub-challenge (CCS) database in the INTERSPEECH Computational Paralinguistics challengE (ComParE) challenge and the DiCOVA Track-1 database. By training four simple convolutional neural networks (CNNs) in the transfer learning framework, our approach achieves an absolute improvement of 3.57% over the baseline of DiCOVA Track-1 validation of the area under the receiver operating characteristic curve (ROC AUC) and an absolute improvement of 1.73% over the baseline of ComParE CCS test unweighted average recall (UAR).
Organisation(s): L3S Research Centre
External Organisation(s): Imperial College London
University of Augsburg
Type: Article
Journal: Frontiers in digital health
Volume: 3
ISSN: 2673-253X
Publication date: 03.01.2022
Publication status: Published
Peer reviewed: Yes
ASJC Scopus subject areas: Health Informatics, Computer Science Applications, Biomedical Engineering, Medicine (miscellaneous)
Electronic version(s): https://doi.org/10.3389/fdgth.2021.799067 (Access: Open)

BibTeX

@article{4eba3074118e456d84b837e04d5a18b3,
title = "CovNet: A Transfer Learning Framework for Automatic COVID-19 Detection From Crowd-Sourced Cough Sounds",
abstract = "Since the COronaVIrus Disease 2019 (COVID-19) outbreak, developing a digital diagnostic tool to detect COVID-19 from respiratory sounds with computer audition has become an essential topic due to its advantages of being swift, low-cost, and eco-friendly. However, prior studies mainly focused on small-scale COVID-19 datasets. To build a robust model, the large-scale multi-sound FluSense dataset is utilised to help detect COVID-19 from cough sounds in this study. Due to the gap between FluSense and the COVID-19-related datasets consisting of cough only, the transfer learning framework (namely CovNet) is proposed and applied rather than simply augmenting the training data with FluSense. The CovNet contains (i) a parameter transferring strategy and (ii) an embedding incorporation strategy. Specifically, to validate the CovNet's effectiveness, it is used to transfer knowledge from FluSense to COUGHVID, a large-scale cough sound database of COVID-19 negative and COVID-19 positive individuals. The trained model on FluSense and COUGHVID is further applied under the CovNet to another two small-scale cough datasets for COVID-19 detection, the COVID-19 cough sub-challenge (CCS) database in the INTERSPEECH Computational Paralinguistics challengE (ComParE) challenge and the DiCOVA Track-1 database. By training four simple convolutional neural networks (CNNs) in the transfer learning framework, our approach achieves an absolute improvement of 3.57% over the baseline of DiCOVA Track-1 validation of the area under the receiver operating characteristic curve (ROC AUC) and an absolute improvement of 1.73% over the baseline of ComParE CCS test unweighted average recall (UAR).",
keywords = "cough, COUGHVID, COVID-19, FluSense, transfer learning",
author = "Yi Chang and Xin Jing and Zhao Ren and Schuller, {Bj{\"o}rn W.}",
note = "FUNDING: This study was partially supported by the Horizon H2020 Marie Sk{\l}odowska-Curie Actions Initial Training Network European Training Network (MSCA-ITN-ETN) project under grant agreement No. 766287 (TAPAS), the DFG{\textquoteright}s Reinhart Koselleck project No. 442218748 (AUDI0NOMOUS), and the Federal Ministry of Education and Research (BMBF), Germany under the project LeibnizKILabor (Grant No. 01DD20003).",
year = "2022",
month = jan,
day = "3",
doi = "10.3389/fdgth.2021.799067",
language = "English",
volume = "3",
journal = "Frontiers in digital health",
issn = "2673-253X",
publisher = "Frontiers Media S.A.",
}