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).
Highlights
Since the year 2019, the coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has become a global pandemic1
We propose a hybrid transfer learning framework for robust COVID-19 detection, where several convolutional neural networks (CNNs) are trained on large-scale databases and fine-tuned on several small-scale cough sound databases for verification
Note that the focus of this paper is not to outperform the state-of-the-art neural networks models for COVID-19 detection from cough sounds; rather, the aim of this study is to provide a framework for mitigating the effect of noise or irrelevant sounds in the crowd-sourcing datasets applied to COVID-19 by training robust CNN models with the transferred knowledge from Flusense and/or COUGHVID
Summary
Since the year 2019, the coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has become a global pandemic. As of August 2021, there have been more than 202, 000, 000 confirmed cases of COVID-19 worldwide, including more than 4, 000, 000 deaths, reported by the World Health Organization (WHO). The reverse transcription PCR (RT-PCR) from oral-nasopharyngeal swabs identifies viral RNA and is a commonly used instrument for the diagnosis of COVID19. Serological instruments are utilised to diagnose/confirm late COVID-19 cases by measuring antibody responses to the corresponding infection [5]. Compared to the above laboratory instruments, which require professionals and special medical equipment, rapid antigen and molecular tests using nasopharyngeal swabs are commercially available due to their swift and simple test procedures, reduced mortality of COVID-19 patients, internal hospital costs, and in-hospital transmission [6]. Rapid tests are still hard-to-follow for non-specialists and are not environment-friendly
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
