A novel cough audio segmentation framework for COVID-19 detection

Alice Ashby; Julia A. Meister; Goran Soldar; Khuong An Nguyen

doi:10.14236/ewic/ODAK22.1

A novel cough audio segmentation framework for COVID-19 detection

Alice Ashby, Julia A. Meister, Goran Soldar, Khuong An Nguyen

Department of Computer Science

Research output: Contribution to conference › Paper › peer-review

Abstract

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.

Original language	English
Pages	1-8
Number of pages	8
DOIs	https://doi.org/10.14236/ewic/ODAK22.1
Publication status	Published - 1 Jul 2022

Keywords

audio pre-processing
audio noise filtering
cough segmentation
COVID-19 open datasets

Access to Document

10.14236/ewic/ODAK22.1Licence: CC BY

https://universityofbrighton.github.io/odak

Cite this

@conference{a756d3a0087647ed9b5f5376a618c80c,

title = "A novel cough audio segmentation framework for COVID-19 detection",

abstract = "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.",

keywords = "audio pre-processing, audio noise filtering, cough segmentation, COVID-19 open datasets",

author = "Alice Ashby and Meister, {Julia A.} and Goran Soldar and Nguyen, {Khuong An}",

note = "Symposium on Open Data and Knowledge for a Post-Pandemic Era, ODAK 2022 ; Conference date: 30-06-2022 Through 01-07-2022",

year = "2022",

month = jul,

day = "1",

doi = "10.14236/ewic/ODAK22.1",

language = "English",

pages = "1--8",

}

TY - CONF

T1 - A novel cough audio segmentation framework for COVID-19 detection

AU - Ashby, Alice

AU - Meister, Julia A.

AU - Soldar, Goran

AU - Nguyen, Khuong An

N1 - Symposium on Open Data and Knowledge for a Post-Pandemic Era, ODAK 2022 ; Conference date: 30-06-2022 Through 01-07-2022

PY - 2022/7/1

Y1 - 2022/7/1

N2 - 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.

AB - 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.

KW - audio pre-processing

KW - audio noise filtering

KW - cough segmentation

KW - COVID-19 open datasets

U2 - 10.14236/ewic/ODAK22.1

DO - 10.14236/ewic/ODAK22.1

M3 - Paper

SP - 1

EP - 8

ER -