Acoustic analysis assessment in speech pathology detection
Automatic detection of voice pathologies enables non-invasive, low cost and objective assessments of the presence of disorders, as well as accelerating and improving the process of diagnosis and clinical treatment given to patients. In this work, a vector made up of 28 acoustic parameters is evaluat...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Sciendo
2015-09-01
|
Series: | International Journal of Applied Mathematics and Computer Science |
Subjects: | |
Online Access: | https://doi.org/10.1515/amcs-2015-0046 |
id |
doaj-5aed07aaff8f4d68b9d1e0036e9eb414 |
---|---|
record_format |
Article |
spelling |
doaj-5aed07aaff8f4d68b9d1e0036e9eb4142021-09-06T19:39:48ZengSciendoInternational Journal of Applied Mathematics and Computer Science2083-84922015-09-0125363164310.1515/amcs-2015-0046amcs-2015-0046Acoustic analysis assessment in speech pathology detectionPanek Daria0Skalski Andrzej1Gajda Janusz2Tadeusiewicz Ryszard3Department of Measurement and Electronics AGH University of Science and Technology, Al. Mickiewicza 30, 30-059 Kraków, PolandDepartment of Measurement and Electronics AGH University of Science and Technology, Al. Mickiewicza 30, 30-059 Kraków, PolandDepartment of Measurement and Electronics AGH University of Science and Technology, Al. Mickiewicza 30, 30-059 Kraków, PolandDepartment of Automatics and Biomedical Engineering AGH University of Science and Technology, Al. Mickiewicza 30, 30-059 Kraków, PolandAutomatic detection of voice pathologies enables non-invasive, low cost and objective assessments of the presence of disorders, as well as accelerating and improving the process of diagnosis and clinical treatment given to patients. In this work, a vector made up of 28 acoustic parameters is evaluated using principal component analysis (PCA), kernel principal component analysis (kPCA) and an auto-associative neural network (NLPCA) in four kinds of pathology detection (hyperfunctional dysphonia, functional dysphonia, laryngitis, vocal cord paralysis) using the a, i and u vowels, spoken at a high, low and normal pitch. The results indicate that the kPCA and NLPCA methods can be considered a step towards pathology detection of the vocal folds. The results show that such an approach provides acceptable results for this purpose, with the best efficiency levels of around 100%. The study brings the most commonly used approaches to speech signal processing together and leads to a comparison of the machine learning methods determining the health status of the patienthttps://doi.org/10.1515/amcs-2015-0046linear pcanon-linear pcaauto-associative neural networkvalidationvoice pathology detection |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Panek Daria Skalski Andrzej Gajda Janusz Tadeusiewicz Ryszard |
spellingShingle |
Panek Daria Skalski Andrzej Gajda Janusz Tadeusiewicz Ryszard Acoustic analysis assessment in speech pathology detection International Journal of Applied Mathematics and Computer Science linear pca non-linear pca auto-associative neural network validation voice pathology detection |
author_facet |
Panek Daria Skalski Andrzej Gajda Janusz Tadeusiewicz Ryszard |
author_sort |
Panek Daria |
title |
Acoustic analysis assessment in speech pathology detection |
title_short |
Acoustic analysis assessment in speech pathology detection |
title_full |
Acoustic analysis assessment in speech pathology detection |
title_fullStr |
Acoustic analysis assessment in speech pathology detection |
title_full_unstemmed |
Acoustic analysis assessment in speech pathology detection |
title_sort |
acoustic analysis assessment in speech pathology detection |
publisher |
Sciendo |
series |
International Journal of Applied Mathematics and Computer Science |
issn |
2083-8492 |
publishDate |
2015-09-01 |
description |
Automatic detection of voice pathologies enables non-invasive, low cost and objective assessments of the presence of disorders, as well as accelerating and improving the process of diagnosis and clinical treatment given to patients. In this work, a vector made up of 28 acoustic parameters is evaluated using principal component analysis (PCA), kernel principal component analysis (kPCA) and an auto-associative neural network (NLPCA) in four kinds of pathology detection (hyperfunctional dysphonia, functional dysphonia, laryngitis, vocal cord paralysis) using the a, i and u vowels, spoken at a high, low and normal pitch. The results indicate that the kPCA and NLPCA methods can be considered a step towards pathology detection of the vocal folds. The results show that such an approach provides acceptable results for this purpose, with the best efficiency levels of around 100%. The study brings the most commonly used approaches to speech signal processing together and leads to a comparison of the machine learning methods determining the health status of the patient |
topic |
linear pca non-linear pca auto-associative neural network validation voice pathology detection |
url |
https://doi.org/10.1515/amcs-2015-0046 |
work_keys_str_mv |
AT panekdaria acousticanalysisassessmentinspeechpathologydetection AT skalskiandrzej acousticanalysisassessmentinspeechpathologydetection AT gajdajanusz acousticanalysisassessmentinspeechpathologydetection AT tadeusiewiczryszard acousticanalysisassessmentinspeechpathologydetection |
_version_ |
1717769984787087360 |