{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,15]],"date-time":"2024-09-15T16:10:25Z","timestamp":1726416625292},"reference-count":58,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,1,3]],"date-time":"2022-01-03T00:00:00Z","timestamp":1641168000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Digit. Health"],"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).<\/jats:p>","DOI":"10.3389\/fdgth.2021.799067","type":"journal-article","created":{"date-parts":[[2022,1,3]],"date-time":"2022-01-03T06:22:42Z","timestamp":1641190962000},"update-policy":"http:\/\/dx.doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["CovNet: A Transfer Learning Framework for Automatic COVID-19 Detection From Crowd-Sourced Cough Sounds"],"prefix":"10.3389","volume":"3","author":[{"given":"Yi","family":"Chang","sequence":"first","affiliation":[]},{"given":"Xin","family":"Jing","sequence":"additional","affiliation":[]},{"given":"Zhao","family":"Ren","sequence":"additional","affiliation":[]},{"given":"Bj\u00f6rn W.","family":"Schuller","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2022,1,3]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.amsu.2020.06.010","article-title":"Is the lockdown important to prevent the COVID-19 pandemic? Effects on psychology, environment and economy-perspective","volume":"56","author":"Atalan","year":"2020","journal-title":"Ann Med Surg"},{"key":"B2","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1177\/1010539520940893","article-title":"Risk of an increase in suicide rates associated with economic downturn due to COVID-19 pandemic","volume":"32","author":"Inoue","year":"2020","journal-title":"Asia Pac J Public Health"},{"key":"B3","doi-asserted-by":"publisher","first-page":"14","DOI":"10.3389\/fdgth.2021.564906","article-title":"COVID-19 and computer audition: an overview on what speech & sound analysis could contribute in the SARS-CoV-2 corona crisis","volume":"3","author":"Schuller","year":"2021","journal-title":"Front Digit Health"},{"key":"B4","doi-asserted-by":"publisher","first-page":"903","DOI":"10.1002\/jmv.25786","article-title":"Stability issues of RT-PCR testing of SARS-CoV-2 for hospitalized patients clinically diagnosed with COVID-19","volume":"92","author":"Li","year":"2020","journal-title":"J Med Virol"},{"key":"B5","doi-asserted-by":"publisher","first-page":"e00512","DOI":"10.1128\/JCM.00512-20","article-title":"Laboratory diagnosis of COVID-19: Current issues and challenges","volume":"58","author":"Tang","year":"2020","journal-title":"J Clin Microbiol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1002\/14651858.CD013705.pub2","article-title":"Rapid, point-of-care antigen and molecular-based tests for diagnosis of SARS-CoV-2 infection","volume":"3","author":"Dinnes","year":"2021","journal-title":"Cochrane Database Syst Rev"},{"key":"B7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/B978-0-12-818130-0.00001-5","article-title":"Chapter 1: Speech processing in healthcare: can we integrate?","volume-title":"Intelligent Speech Signal Processing","author":"Santosh","year":"2019"},{"key":"B8","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s10916-020-01681-9","article-title":"Automatic lung health screening using respiratory sounds","volume":"45","author":"Mukherjee","year":"2021","journal-title":"J Med Syst"},{"key":"B9","doi-asserted-by":"publisher","first-page":"2157008","DOI":"10.1142\/S0218001421570081","article-title":"Lung health analysis: adventitious respiratory sound classification using filterbank energies","volume":"2021","author":"Mukherjee","year":"2021","journal-title":"Int J Pattern Recogn Artif Intell"},{"key":"B10","doi-asserted-by":"publisher","first-page":"473","DOI":"10.3389\/fpubh.2020.00473","article-title":"Modeling the onset of symptoms of COVID-19","volume":"8","author":"Larsen","year":"2020","journal-title":"Front Public Health"},{"key":"B11","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1080\/03091902.2020.1822941","article-title":"Return to school in the COVID-19 era: considerations for temperature measurement","volume":"44","author":"Buoite Stella","year":"2020","journal-title":"J Med Eng Technol"},{"key":"B12","first-page":"701","article-title":"A real-time robot-based auxiliary system for risk evaluation of COVID-19 infection","volume-title":"Proc. Interspeech","author":"Wei","year":"2020"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3097559","article-title":"Cough sound detection and diagnosis using artificial intelligence techniques: challenges and opportunities","author":"Alqudaihi","year":"2021","journal-title":"IEEE Access"},{"key":"B14","doi-asserted-by":"publisher","first-page":"100378","DOI":"10.1016\/j.imu.2020.100378","article-title":"AI4COVID-19: AI enabled preliminary diagnosis for COVID-19 from cough samples via an app","volume":"20","author":"Imran","year":"2020","journal-title":"Inform Med Unlocked"},{"key":"B15","first-page":"3474","article-title":"Exploring automatic diagnosis of COVID-19 from crowdsourced respiratory sound data","volume-title":"Proc. ACM SIGKDD","author":"Brown","year":"2020"},{"key":"B16","first-page":"4811","article-title":"Coswara\u2013a database of breathing, cough, and voice sounds for COVID-19 diagnosis","volume-title":"Proc. Interspeech","author":"Sharma","year":"2020"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-021-00937-4","article-title":"The COUGHVID crowdsourcing dataset, a corpus for the study of large-scale cough analysis algorithms","volume":"8","author":"Orlandic","year":"2021","journal-title":"Sci Data"},{"key":"B18","first-page":"1","article-title":"FluSense: a contactless syndromic surveillance platform for influenza-like illness in hospital waiting areas","volume-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies","author":"Al Hossain","year":"2020"},{"key":"B19","doi-asserted-by":"crossref","first-page":"431","DOI":"10.21437\/Interspeech.2021-19","article-title":"The INTERSPEECH 2021 computational paralinguistics challenge: COVID-19 cough, COVID-19 speech, escalation & primates","volume-title":"Proc. Interspeech","author":"Schuller","year":"2021"},{"key":"B20","doi-asserted-by":"crossref","first-page":"901","DOI":"10.21437\/Interspeech.2021-74","article-title":"DiCOVA challenge: dataset, task, and baseline system for COVID-19 diagnosis using acoustics","volume-title":"Proc. Interspeech","author":"Muguli","year":"2021"},{"key":"B21","doi-asserted-by":"crossref","first-page":"242","DOI":"10.4018\/978-1-60566-766-9.ch011","article-title":"Transfer learning","volume-title":"Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques","author":"Torrey","year":"2010"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"Pan","year":"2010","journal-title":"IEEE Trans Knowledge Data Eng"},{"key":"B23","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1016\/j.neucom.2017.01.018","article-title":"Plant identification using deep neural networks via optimization of transfer learning parameters","volume":"235","author":"Mehdipour Ghazi","year":"2017","journal-title":"Neurocomputing"},{"key":"B24","first-page":"407","article-title":"Adaptive transfer learning","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Cao","year":"2010"},{"key":"B25","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","article-title":"ImageNet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun ACM"},{"key":"B26","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2019.00277","article-title":"Do better imagenet models transfer better? In: Proc","volume-title":"CVPR","author":"Kornblith","year":"2019"},{"key":"B27","doi-asserted-by":"publisher","first-page":"104115","DOI":"10.1016\/j.compbiomed.2020.104115","article-title":"A scoping review of transfer learning research on medical image analysis using ImageNet","volume":"128","author":"Morid","year":"2021","journal-title":"Comput Biol Med"},{"volume-title":"Transfusion: Understanding Transfer Learning for Medical Imaging","year":"2019","author":"Raghu","key":"B28"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1109\/TMI.2016.2528162","article-title":"Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning","volume":"35","author":"Shin","year":"2016","journal-title":"IEEE Trans Med Imaging"},{"key":"B30","first-page":"16","article-title":"Training neural audio classifiers with few data","volume-title":"Proc. ICASSP","author":"Pons","year":"2019"},{"key":"B31","first-page":"326","article-title":"Knowledge transfer from weakly labeled audio using convolutional neural network for sound events and scenes","volume-title":"Proc. ICASSP","author":"Kumar","year":"2018"},{"key":"B32","doi-asserted-by":"publisher","first-page":"2880","DOI":"10.1109\/TASLP.2020.3030497","article-title":"PANNs: Large-scale pretrained audio neural networks for audio pattern recognition","volume":"28","author":"Kong","year":"2020","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"B33","first-page":"5329","article-title":"X-vectors: robust DNN embeddings for speaker recognition","volume-title":"Proc. ICASSP","author":"Snyder","year":"2018"},{"key":"B34","doi-asserted-by":"crossref","first-page":"818","DOI":"10.1007\/978-3-319-10590-1_53","article-title":"Visualizing and understanding convolutional networks","volume-title":"Computer Vision-ECCV 2014","author":"Zeiler","year":"2014"},{"key":"B35","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.251","article-title":"CNN-RNN: a unified framework for multi-label image classification","volume-title":"Proc. CVPR","author":"Wang","year":"2016"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1901","DOI":"10.1109\/TPAMI.2015.2491929","article-title":"HCP: a flexible CNN framework for multi-label image classification","volume":"38","author":"Wei","year":"2016","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"B37","first-page":"844","article-title":"Medical image classification with convolutional neural network","volume-title":"Proc. ICARCV","author":"Li","year":"2014"},{"key":"B38","first-page":"7184","article-title":"Generating and protecting against adversarial attacks for deep speech-based emotion recognition models","volume-title":"Proc. ICASSP","author":"Ren","year":"2020"},{"key":"B39","doi-asserted-by":"publisher","first-page":"1791","DOI":"10.1109\/TASLP.2019.2930913","article-title":"Weakly labelled AudioSet tagging with attention neural networks","volume":"27","author":"Kong","year":"2019","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"B40","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. ICLR","author":"Simonyan","year":"2015"},{"key":"B41","first-page":"770","article-title":"Deep residual learning for image recognition","volume-title":"Proc. CVPR","author":"He","year":"2016"},{"key":"B42","unstructured":"MobileNets: efficient convolutional neural networks for mobile vision applications HowardAG ZhuM ChenB KalenichenkoD WangW WeyandT arXiv [Preprint]. arXiv2017"},{"key":"B43","first-page":"448","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. ICML.","author":"Ioffe","year":"2015"},{"key":"B44","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","volume-title":"Proc. ICML","author":"Nair","year":"2010"},{"key":"B45","unstructured":"Dropout: a simple way to prevent neural networks from overfitting192958 SrivastavaN HintonG KrizhevskyA SutskeverI SalakhutdinovR J Mach Learn Res152014"},{"key":"B46","doi-asserted-by":"publisher","first-page":"2850","DOI":"10.1007\/s10489-020-02055-x","article-title":"Attention-based VGG-16 model for COVID-19 chest X-ray image classification","volume":"51","author":"Sitaula","year":"2021","journal-title":"Appl Intell"},{"key":"B47","doi-asserted-by":"publisher","first-page":"1319","DOI":"10.1016\/j.aej.2021.06.024","article-title":"Automatic diagnosis of COVID-19 disease using deep convolutional neural network with multi-feature channel from respiratory sound data: cough, voice, and breath","volume":"61","author":"Lella","year":"2021","journal-title":"Alexandria Eng J"},{"key":"B48","first-page":"131","article-title":"CNN architectures for large-scale audio classification","volume-title":"Proc. ICASSP","author":"Hershey","year":"2017"},{"key":"B49","first-page":"776","article-title":"Audio Set: An ontology and human-labeled dataset for audio events","volume-title":"Proc. ICASSP","author":"Gemmeke","year":"2017"},{"key":"B50","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1136\/bmjinnov-2021-000668","article-title":"End-to-end convolutional neural network enables COVID-19 detection from breath and cough audio: a pilot study","volume":"7","author":"Coppock","year":"2021","journal-title":"BMJ Innovations"},{"key":"B51","doi-asserted-by":"publisher","first-page":"102365","DOI":"10.1016\/j.bspc.2020.102365","article-title":"Application of deep learning techniques for detection of COVID-19 cases using chest X-ray images: a comprehensive study","volume":"64","author":"Nayak","year":"2021","journal-title":"Biomed Signal Process Control"},{"key":"B52","doi-asserted-by":"crossref","DOI":"10.1002\/9781118706664","volume-title":"Computational Paralinguistics: Emotion, Affect and Personality in Speech and Language Processing","author":"Schuller","year":"2013"},{"key":"B53","doi-asserted-by":"crossref","first-page":"2242","DOI":"10.21437\/Interspeech.2012-131","article-title":"Classifying skewed data: importance weighting to optimize average recall","volume-title":"Proc. Interspeech","author":"Rosenberg","year":"2012"},{"key":"B54","doi-asserted-by":"crossref","first-page":"916","DOI":"10.21437\/Interspeech.2021-2191","article-title":"Detecting COVID-19 from audio recording of coughs using random forests and support vector machines","volume-title":"Proc. Interspeech","author":"Sodergren","year":"2021"},{"key":"B55","doi-asserted-by":"crossref","first-page":"921","DOI":"10.21437\/Interspeech.2021-497","article-title":"Diagnosis of COVID-19 using auditory acoustic cues","volume-title":"Proc. Interspeech","author":"Das","year":"2021"},{"key":"B56","doi-asserted-by":"publisher","first-page":"926","DOI":"10.21437\/Interspeech.2021-799","article-title":"Classification of COVID-19 from cough using autoregressive predictive coding pretraining and spectral data augmentation","author":"Harvill","year":"2021","journal-title":"Proc. Interspeech"},{"key":"B57","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/A:1007379606734","article-title":"Multitask learning","volume":"28","author":"Caruana","year":"1997","journal-title":"Mach Learn"},{"key":"B58","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.neucom.2018.05.083","article-title":"Deep visual domain adaptation: a survey","volume":"312","author":"Wang","year":"2018","journal-title":"Neurocomputing"}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2021.799067\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,15]],"date-time":"2024-09-15T15:12:27Z","timestamp":1726413147000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2021.799067\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,3]]},"references-count":58,"alternative-id":["10.3389\/fdgth.2021.799067"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2021.799067","relation":{},"ISSN":["2673-253X"],"issn-type":[{"type":"electronic","value":"2673-253X"}],"subject":[],"published":{"date-parts":[[2022,1,3]]}}}