A novel cough audio segmentation framework for COVID-19 detection

Despite its potential, Machine Learning has played little role in the present pandemic, due to the lack of data (i.e., there were not many COVID-19 samples in the early stage). Thus, this paper proposes a novel cough audio segmentation framework that may be applied on top of existing COVID-19 cough datasets to increase the number of samples, as well as filtering out noises and uninformative data. We demonstrate the efficiency of our framework on two popular open datasets.

Content

Author and article information

Contributors

Alice E. Ashby

Julia A. Meister

Goran Soldar

Khuong An Nguyen

Conference

Publication date (Print): July 2022

Pages: 1-8

Affiliations

[0001]University of Brighton

East Sussex, BN2 4GJ

United Kingdom

Article

DOI: 10.14236/ewic/ODAK22.1

SO-VID: 9f20f36d-61c5-4396-983a-39258bad1e37

License:

This work is licensed under a Creative Commons Attribution 4.0 Unported License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

Conference name: Proceedings of the Symposium on Open Data and Knowledge for a Post-Pandemic Era ODAK22, UK

Conference acronym: ODAK 2022

Conference number:

Conference location: Brighton, UK

Conference date: June 30-July 1, 2022

Conference sponsor: Electronic Workshops in Computing (eWiC)

Conference theme: Open Data and Knowledge for a Post-Pandemic Era

History

Product

1477-9358 BCS Learning & Development

Self URI (article page): https://www.scienceopen.com/hosted-document?doi=10.14236/ewic/ODAK22.1

Self URI (journal page): https://ewic.bcs.org/

REFERENCES

J HanC BrownJ ChauhanA GrammenosA HasthanasombatD SpathisT XiaP CicutaC Mascolo 2021 Exploring automatic COVID-19 diagnosis via voice and symptoms from crowdsourced data ICASSP 2021 International Conference on Acoustics, Speech and Signal Processing (ICASSP) 8328 8332 IEEE
M PaharM KlopperR WarrenT Niesler 2021 COVID-19 cough classification using machine learning and global smartphone recordings Computers in Biology and Medicine 135 104572
J.F GemmekeD.P EllisD FreedmanA JansenW LawrenceR.C MooreM PlakalM Ritter 2017 Audio set: An ontology and humanlabeled dataset for audio events 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP) 776 780 IEEE
M Cohen-McFarlaneR GoubranF Knoefel 2020 Novel coronavirus cough database: Nococoda Ieee Access 8 154087 154094
T XiaD SpathisJ ChA GrammenosJ HanA HasthanasombatE BondarevaT DangA FlotoP CicutaC Mascolo 2021 August COVID-19 Sounds: A Large-Scale Audio Dataset for Digital Respiratory Screening Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track
P BagadA DalmiaJ DoshiA NagraniP BhamareA MahaleS RaneN AgarwalR Panicker 2020 Cough against covid: Evidence of covid-19 signature in cough sounds arXiv preprint arXiv:2009.08790
D.T PizzoS EstebanM Scetta 2021 IATos: AI-powered pre-screening tool for COVID-19 from cough audio samples arXiv preprint arXiv:2104.13247
N SharmaP KrishnanR KumarS RamojiS.R ChetupalliP.K GhoshS Ganapathy 2020 Coswara–a database of breathing, cough, and voice sounds for COVID-19 diagnosis arXiv preprint arXiv:2005.10548
L OrlandicT TeijeiroD Atienza 2021 The COUGHVID crowdsourcing dataset, a corpus for the study of large-scale cough analysis algorithms Scientific Data 8 1 1 10
G ChaudhariX JiangA FakhryA HanJ XiaoS ShenA Khanzada 2020 Virufy: Global applicability of crowdsourced and clinical datasets for AI detection of COVID-19 from cough arXiv preprint arXiv:2011.13320
J.A MeisterK.A NguyenZ Luo 2021 Audio feature ranking for sound-based COVID-19 patient detection arXiv preprint arXiv:2104.07128
A MurataY TaniguchiY HashimotoY KanekoY TakasakiS Kudoh 1998 Discrimination of productive and non-productive cough by sound analysis Internal Medicine 37 9 732 735
S.H ShinT HashimotoS Hatano 2008 Automatic detection system for cough sounds as a symptom of abnormal health condition IEEE Transactions on Information Technology in Biomedicine 13 4 486 493
Y.A AmrullohU.R AbeyratneV SwarnkarR TriasihA Setyati 2015 Automatic cough segmentation from non-contact sound recordings in pediatric wards Biomedical Signal Processing and Control 21 126 136
C InfanteD ChamberlainR FletcherY ThoratR Kodgule 2017 October Use of cough sounds for diagnosis and screening of pulmonary disease 2017 IEEE Global Humanitarian Technology Conference (GHTC) 1 10 IEEE

Comments

Comment on this article

[1] J HanC BrownJ ChauhanA GrammenosA HasthanasombatD SpathisT XiaP CicutaC Mascolo 2021 Exploring automatic COVID-19 diagnosis via voice and symptoms from crowdsourced data ICASSP 2021 International Conference on Acoustics, Speech and Signal Processing (ICASSP) 8328 8332 IEEE

[2] M PaharM KlopperR WarrenT Niesler 2021 COVID-19 cough classification using machine learning and global smartphone recordings Computers in Biology and Medicine 135 104572

[3] J.F GemmekeD.P EllisD FreedmanA JansenW LawrenceR.C MooreM PlakalM Ritter 2017 Audio set: An ontology and humanlabeled dataset for audio events 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP) 776 780 IEEE

[4] M Cohen-McFarlaneR GoubranF Knoefel 2020 Novel coronavirus cough database: Nococoda Ieee Access 8 154087 154094

[5] T XiaD SpathisJ ChA GrammenosJ HanA HasthanasombatE BondarevaT DangA FlotoP CicutaC Mascolo 2021 August COVID-19 Sounds: A Large-Scale Audio Dataset for Digital Respiratory Screening Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track

[6] P BagadA DalmiaJ DoshiA NagraniP BhamareA MahaleS RaneN AgarwalR Panicker 2020 Cough against covid: Evidence of covid-19 signature in cough sounds arXiv preprint arXiv:2009.08790

[7] D.T PizzoS EstebanM Scetta 2021 IATos: AI-powered pre-screening tool for COVID-19 from cough audio samples arXiv preprint arXiv:2104.13247

[8] N SharmaP KrishnanR KumarS RamojiS.R ChetupalliP.K GhoshS Ganapathy 2020 Coswara–a database of breathing, cough, and voice sounds for COVID-19 diagnosis arXiv preprint arXiv:2005.10548

[9] L OrlandicT TeijeiroD Atienza 2021 The COUGHVID crowdsourcing dataset, a corpus for the study of large-scale cough analysis algorithms Scientific Data 8 1 1 10

[10] G ChaudhariX JiangA FakhryA HanJ XiaoS ShenA Khanzada 2020 Virufy: Global applicability of crowdsourced and clinical datasets for AI detection of COVID-19 from cough arXiv preprint arXiv:2011.13320

[11] J.A MeisterK.A NguyenZ Luo 2021 Audio feature ranking for sound-based COVID-19 patient detection arXiv preprint arXiv:2104.07128

[12] A MurataY TaniguchiY HashimotoY KanekoY TakasakiS Kudoh 1998 Discrimination of productive and non-productive cough by sound analysis Internal Medicine 37 9 732 735

[13] S.H ShinT HashimotoS Hatano 2008 Automatic detection system for cough sounds as a symptom of abnormal health condition IEEE Transactions on Information Technology in Biomedicine 13 4 486 493

[14] Y.A AmrullohU.R AbeyratneV SwarnkarR TriasihA Setyati 2015 Automatic cough segmentation from non-contact sound recordings in pediatric wards Biomedical Signal Processing and Control 21 126 136

[15] C InfanteD ChamberlainR FletcherY ThoratR Kodgule 2017 October Use of cough sounds for diagnosis and screening of pulmonary disease 2017 IEEE Global Humanitarian Technology Conference (GHTC) 1 10 IEEE

Celebrating 65 years of The Computer Journal - free-to-read perspectives - bcs.org/tcj65