Audio-cough event detection based on moment theory

Jesus Monge-Alvarez, Carlos Hoyos Barceló, Keshav Dahal, Juan Pablo Casaseca

Research output: Contribution to journalArticle

87 Downloads (Pure)

Abstract

Cough detection has recently been identified as of paramount importance to fully exploit the potential of telemedicine in respiratory conditions and release some of the economic burden of respiratory care in national health systems. Current audio-based cough detection systems are either uncomfortable or not suitable for continuous patient monitoring, since the audio processing methods implemented therein fail to cope with noisy environments such as those where the acquiring device is carried in the pocket (e.g. smartphone). Moment theory has been widely applied in a number of complex problems involving image processing, computer vision, and pattern recognition. Their invariance properties and noise robustness make them especially suitable as “signature” features enabling character recognition or texture analysis. A natural extension of moment theory to one-dimensional signals is the identification of meaningful patterns in audio signals. However, to the best of our knowledge only marginal attempts have been made in this direction. This paper applies moment theory to perform cough detection in noisy audio signals. Our proposal adopts the first steps used to extract Mel frequency cepstral coefficients (time-frequency decomposition and application of a filter bank defined in the Mel scale) while the innovation is introduced in the second step, where energy patterns defined for specific temporal frames and frequency bands are characterised using moment theory. Our results show the feasibility of using moment theory to solve such a problem in a variety of noise conditions, with sensitivity and specificity values around 90%, significantly outperforming popular state-of-the-art feature sets.
Original languageEnglish
Pages (from-to)124-135
JournalApplied Acoustics
Volume135
Early online date17 Feb 2018
DOIs
Publication statusPublished - 1 Jun 2018

Fingerprint

cough
moments
audio signals
telemedicine
character recognition
computer vision
pattern recognition
health
image processing
economics
proposals
invariance
textures
signatures
decomposition
filters
sensitivity
coefficients

Cite this

Monge-Alvarez, Jesus ; Hoyos Barceló, Carlos ; Dahal, Keshav ; Casaseca, Juan Pablo. / Audio-cough event detection based on moment theory. In: Applied Acoustics . 2018 ; Vol. 135. pp. 124-135.
@article{76c982f0041a41309cb6bb83c98f8c6f,
title = "Audio-cough event detection based on moment theory",
abstract = "Cough detection has recently been identified as of paramount importance to fully exploit the potential of telemedicine in respiratory conditions and release some of the economic burden of respiratory care in national health systems. Current audio-based cough detection systems are either uncomfortable or not suitable for continuous patient monitoring, since the audio processing methods implemented therein fail to cope with noisy environments such as those where the acquiring device is carried in the pocket (e.g. smartphone). Moment theory has been widely applied in a number of complex problems involving image processing, computer vision, and pattern recognition. Their invariance properties and noise robustness make them especially suitable as “signature” features enabling character recognition or texture analysis. A natural extension of moment theory to one-dimensional signals is the identification of meaningful patterns in audio signals. However, to the best of our knowledge only marginal attempts have been made in this direction. This paper applies moment theory to perform cough detection in noisy audio signals. Our proposal adopts the first steps used to extract Mel frequency cepstral coefficients (time-frequency decomposition and application of a filter bank defined in the Mel scale) while the innovation is introduced in the second step, where energy patterns defined for specific temporal frames and frequency bands are characterised using moment theory. Our results show the feasibility of using moment theory to solve such a problem in a variety of noise conditions, with sensitivity and specificity values around 90{\%}, significantly outperforming popular state-of-the-art feature sets.",
author = "Jesus Monge-Alvarez and {Hoyos Barcel{\'o}}, Carlos and Keshav Dahal and Casaseca, {Juan Pablo}",
year = "2018",
month = "6",
day = "1",
doi = "10.1016/j.apacoust.2018.02.001",
language = "English",
volume = "135",
pages = "124--135",
journal = "Applied Acoustics",
issn = "0003-682X",
publisher = "Elsevier B.V.",

}

Audio-cough event detection based on moment theory. / Monge-Alvarez, Jesus; Hoyos Barceló, Carlos; Dahal, Keshav; Casaseca, Juan Pablo.

In: Applied Acoustics , Vol. 135, 01.06.2018, p. 124-135.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Audio-cough event detection based on moment theory

AU - Monge-Alvarez, Jesus

AU - Hoyos Barceló, Carlos

AU - Dahal, Keshav

AU - Casaseca, Juan Pablo

PY - 2018/6/1

Y1 - 2018/6/1

N2 - Cough detection has recently been identified as of paramount importance to fully exploit the potential of telemedicine in respiratory conditions and release some of the economic burden of respiratory care in national health systems. Current audio-based cough detection systems are either uncomfortable or not suitable for continuous patient monitoring, since the audio processing methods implemented therein fail to cope with noisy environments such as those where the acquiring device is carried in the pocket (e.g. smartphone). Moment theory has been widely applied in a number of complex problems involving image processing, computer vision, and pattern recognition. Their invariance properties and noise robustness make them especially suitable as “signature” features enabling character recognition or texture analysis. A natural extension of moment theory to one-dimensional signals is the identification of meaningful patterns in audio signals. However, to the best of our knowledge only marginal attempts have been made in this direction. This paper applies moment theory to perform cough detection in noisy audio signals. Our proposal adopts the first steps used to extract Mel frequency cepstral coefficients (time-frequency decomposition and application of a filter bank defined in the Mel scale) while the innovation is introduced in the second step, where energy patterns defined for specific temporal frames and frequency bands are characterised using moment theory. Our results show the feasibility of using moment theory to solve such a problem in a variety of noise conditions, with sensitivity and specificity values around 90%, significantly outperforming popular state-of-the-art feature sets.

AB - Cough detection has recently been identified as of paramount importance to fully exploit the potential of telemedicine in respiratory conditions and release some of the economic burden of respiratory care in national health systems. Current audio-based cough detection systems are either uncomfortable or not suitable for continuous patient monitoring, since the audio processing methods implemented therein fail to cope with noisy environments such as those where the acquiring device is carried in the pocket (e.g. smartphone). Moment theory has been widely applied in a number of complex problems involving image processing, computer vision, and pattern recognition. Their invariance properties and noise robustness make them especially suitable as “signature” features enabling character recognition or texture analysis. A natural extension of moment theory to one-dimensional signals is the identification of meaningful patterns in audio signals. However, to the best of our knowledge only marginal attempts have been made in this direction. This paper applies moment theory to perform cough detection in noisy audio signals. Our proposal adopts the first steps used to extract Mel frequency cepstral coefficients (time-frequency decomposition and application of a filter bank defined in the Mel scale) while the innovation is introduced in the second step, where energy patterns defined for specific temporal frames and frequency bands are characterised using moment theory. Our results show the feasibility of using moment theory to solve such a problem in a variety of noise conditions, with sensitivity and specificity values around 90%, significantly outperforming popular state-of-the-art feature sets.

U2 - 10.1016/j.apacoust.2018.02.001

DO - 10.1016/j.apacoust.2018.02.001

M3 - Article

VL - 135

SP - 124

EP - 135

JO - Applied Acoustics

JF - Applied Acoustics

SN - 0003-682X

ER -