Voice Pathology Detection and Classification Using Convolutional Neural Network Model
Voice pathology disorders can be effectively detected using computer-aided voice pathology classification tools. These tools can diagnose voice pathologies at an early stage and offering appropriate treatment. This study aims to develop a powerful feature extraction voice pathology detection tool ba...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-05-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/10/11/3723 |
_version_ | 1797566849271988224 |
---|---|
author | Mazin Abed Mohammed Karrar Hameed Abdulkareem Salama A. Mostafa Mohd Khanapi Abd Ghani Mashael S. Maashi Begonya Garcia-Zapirain Ibon Oleagordia Hosam Alhakami Fahad Taha AL-Dhief |
author_facet | Mazin Abed Mohammed Karrar Hameed Abdulkareem Salama A. Mostafa Mohd Khanapi Abd Ghani Mashael S. Maashi Begonya Garcia-Zapirain Ibon Oleagordia Hosam Alhakami Fahad Taha AL-Dhief |
author_sort | Mazin Abed Mohammed |
collection | DOAJ |
description | Voice pathology disorders can be effectively detected using computer-aided voice pathology classification tools. These tools can diagnose voice pathologies at an early stage and offering appropriate treatment. This study aims to develop a powerful feature extraction voice pathology detection tool based on Deep Learning. In this paper, a pre-trained Convolutional Neural Network (CNN) was applied to a dataset of voice pathology to maximize the classification accuracy. This study also proposes a distinguished training method combined with various training strategies in order to generalize the application of the proposed system on a wide range of problems related to voice disorders. The proposed system has tested using a voice database, namely the Saarbrücken voice database (SVD). The experimental results show the proposed CNN method for speech pathology detection achieves accuracy up to 95.41%. It also obtains 94.22% and 96.13% for F1-Score and Recall. The proposed system shows a high capability of the real-clinical application that offering a fast-automatic diagnosis and treatment solutions within 3 s to achieve the classification accuracy. |
first_indexed | 2024-03-10T19:33:12Z |
format | Article |
id | doaj.art-e7a3f8014340406d93a56a10ea886d8d |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-10T19:33:12Z |
publishDate | 2020-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-e7a3f8014340406d93a56a10ea886d8d2023-11-20T01:58:32ZengMDPI AGApplied Sciences2076-34172020-05-011011372310.3390/app10113723Voice Pathology Detection and Classification Using Convolutional Neural Network ModelMazin Abed Mohammed0Karrar Hameed Abdulkareem1Salama A. Mostafa2Mohd Khanapi Abd Ghani3Mashael S. Maashi4Begonya Garcia-Zapirain5Ibon Oleagordia6Hosam Alhakami7Fahad Taha AL-Dhief8College of Computer Science and Information Technology, University of Anbar, 11, Ramadi 31001, Anbar, IraqCollege of Agriculture, Al-Muthanna University, Samawah 66001, IraqFaculty of Computer Science and Information Technology, Universiti Tun Hussein Onn Malaysia, Batu Pahat 86400, MalaysiaBiomedical Computing and Engineering Technologies (BIOCORE) Applied Research Group, Faculty of Information and Communication Technology, Universiti Teknikal Malaysia Melaka, Durian Tunggal 76100, MalaysiaSoftware Engineering Department, College of Computer and Information Sciences, King Saud University, Riyadh 11451, Saudi ArabiaeVIDA Lab., University of Deusto, Avda/Universidades 24, 48007 Bilbao, SpaineVIDA Lab., University of Deusto, Avda/Universidades 24, 48007 Bilbao, SpainDepartment of Computer Science, College of Computer and Information Systems, Umm Al-Qura University, Makkah 21421, Saudi ArabiaFaculty of Engineering, School of Electrical Engineering, Universiti Teknologi Malaysia (UTM), Johor Bahru 81310, MalaysiaVoice pathology disorders can be effectively detected using computer-aided voice pathology classification tools. These tools can diagnose voice pathologies at an early stage and offering appropriate treatment. This study aims to develop a powerful feature extraction voice pathology detection tool based on Deep Learning. In this paper, a pre-trained Convolutional Neural Network (CNN) was applied to a dataset of voice pathology to maximize the classification accuracy. This study also proposes a distinguished training method combined with various training strategies in order to generalize the application of the proposed system on a wide range of problems related to voice disorders. The proposed system has tested using a voice database, namely the Saarbrücken voice database (SVD). The experimental results show the proposed CNN method for speech pathology detection achieves accuracy up to 95.41%. It also obtains 94.22% and 96.13% for F1-Score and Recall. The proposed system shows a high capability of the real-clinical application that offering a fast-automatic diagnosis and treatment solutions within 3 s to achieve the classification accuracy.https://www.mdpi.com/2076-3417/10/11/3723voice pathology detectionvoice pathology classificationconvolutional neural networkSaarbrücken voice databasethe vowel /a/residual network (ResNet34) |
spellingShingle | Mazin Abed Mohammed Karrar Hameed Abdulkareem Salama A. Mostafa Mohd Khanapi Abd Ghani Mashael S. Maashi Begonya Garcia-Zapirain Ibon Oleagordia Hosam Alhakami Fahad Taha AL-Dhief Voice Pathology Detection and Classification Using Convolutional Neural Network Model Applied Sciences voice pathology detection voice pathology classification convolutional neural network Saarbrücken voice database the vowel /a/ residual network (ResNet34) |
title | Voice Pathology Detection and Classification Using Convolutional Neural Network Model |
title_full | Voice Pathology Detection and Classification Using Convolutional Neural Network Model |
title_fullStr | Voice Pathology Detection and Classification Using Convolutional Neural Network Model |
title_full_unstemmed | Voice Pathology Detection and Classification Using Convolutional Neural Network Model |
title_short | Voice Pathology Detection and Classification Using Convolutional Neural Network Model |
title_sort | voice pathology detection and classification using convolutional neural network model |
topic | voice pathology detection voice pathology classification convolutional neural network Saarbrücken voice database the vowel /a/ residual network (ResNet34) |
url | https://www.mdpi.com/2076-3417/10/11/3723 |
work_keys_str_mv | AT mazinabedmohammed voicepathologydetectionandclassificationusingconvolutionalneuralnetworkmodel AT karrarhameedabdulkareem voicepathologydetectionandclassificationusingconvolutionalneuralnetworkmodel AT salamaamostafa voicepathologydetectionandclassificationusingconvolutionalneuralnetworkmodel AT mohdkhanapiabdghani voicepathologydetectionandclassificationusingconvolutionalneuralnetworkmodel AT mashaelsmaashi voicepathologydetectionandclassificationusingconvolutionalneuralnetworkmodel AT begonyagarciazapirain voicepathologydetectionandclassificationusingconvolutionalneuralnetworkmodel AT ibonoleagordia voicepathologydetectionandclassificationusingconvolutionalneuralnetworkmodel AT hosamalhakami voicepathologydetectionandclassificationusingconvolutionalneuralnetworkmodel AT fahadtahaaldhief voicepathologydetectionandclassificationusingconvolutionalneuralnetworkmodel |