Inter classifier comparison to detect voice pathologies
Voice pathologies are irregular vibrations produced due to vocal folds and various factors malfunctioning. In medical science, novel machine learning algorithms are applied to construct a system to identify disorders that occur invoice. This study aims to extract the features from the audio signals...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2021-04-01
|
| Series: | Mathematical Biosciences and Engineering |
| Subjects: | |
| Online Access: | http://www.aimspress.com/article/doi/10.3934/mbe.2021114?viewType=HTML |
| _version_ | 1818924842988077056 |
|---|---|
| author | Sidra Abid Syed Munaf Rashid Samreen Hussain Anoshia Imtiaz Hamnah Abid Hira Zahid |
| author_facet | Sidra Abid Syed Munaf Rashid Samreen Hussain Anoshia Imtiaz Hamnah Abid Hira Zahid |
| author_sort | Sidra Abid Syed |
| collection | DOAJ |
| description | Voice pathologies are irregular vibrations produced due to vocal folds and various factors malfunctioning. In medical science, novel machine learning algorithms are applied to construct a system to identify disorders that occur invoice. This study aims to extract the features from the audio signals of four chosen diseases from the SVD dataset, such as laryngitis, cyst, non-fluency syndrome, and dysphonia, and then compare the four results of machine learning algorithms, i.e., SVM, Naïve Byes, decision tree and ensemble classifier. In this project, we have used a comparative approach along with the new combination of features to detect voice pathologies which are laryngitis, cyst, non-fluency syndrome, and dysphonia from the SVD dataset. The combination of specific 13 MFCC (mel-frequency cepstral coefficients) features along with pitch, zero crossing rate (ZCR), spectral flux, spectral entropy, spectral centroid, spectral roll-off, and short term energy for more accurate detection of voice pathologies. It is proven that the combination of features extracted gives the best product on the audio, which split into 10 ms. Four machine learning classifiers, SVM, Naïve Bayes, decision tree and ensemble classifier for the inter classifier comparison, give 93.18, 99.45,100 and 51%, respectively. Out of these accuracies, both Naïve Bayes and the decision tree show the most promising results with a higher detection rate. Naïve Bayes and decision tree gives the highest reported outcomes on the selected set of features in the proposed methodology. The SVM has also been concluded to be the commonly used voice condition identification algorithm. |
| first_indexed | 2024-12-20T02:31:46Z |
| format | Article |
| id | doaj.art-df885510285941eb934d7552e2aff8db |
| institution | Directory Open Access Journal |
| issn | 1551-0018 |
| language | English |
| last_indexed | 2024-12-20T02:31:46Z |
| publishDate | 2021-04-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | Mathematical Biosciences and Engineering |
| spelling | doaj.art-df885510285941eb934d7552e2aff8db2022-12-21T19:56:34ZengAIMS PressMathematical Biosciences and Engineering1551-00182021-04-011832258227310.3934/mbe.2021114Inter classifier comparison to detect voice pathologiesSidra Abid Syed0Munaf Rashid1Samreen Hussain2Anoshia Imtiaz3Hamnah Abid4Hira Zahid51. Biomedical Engineering Department & Electrical Engineering Department, Ziauddin University Faculty of Engineering Science Technology and Management, Karachi, Pakistan2. Electrical Engineering Department & Software Engineering Department, Ziauddin University Faculty of Engineering Science Technology and Management, Karachi, Pakistan3. Vice Chancellor, Begum Nusrat Bhutto Women University, Sukkur, Pakistan4. Biomedical Engineering Department, Ziauddin University Faculty of Engineering Science Technology and Management, Karachi, Pakistan4. Biomedical Engineering Department, Ziauddin University Faculty of Engineering Science Technology and Management, Karachi, Pakistan4. Biomedical Engineering Department, Ziauddin University Faculty of Engineering Science Technology and Management, Karachi, PakistanVoice pathologies are irregular vibrations produced due to vocal folds and various factors malfunctioning. In medical science, novel machine learning algorithms are applied to construct a system to identify disorders that occur invoice. This study aims to extract the features from the audio signals of four chosen diseases from the SVD dataset, such as laryngitis, cyst, non-fluency syndrome, and dysphonia, and then compare the four results of machine learning algorithms, i.e., SVM, Naïve Byes, decision tree and ensemble classifier. In this project, we have used a comparative approach along with the new combination of features to detect voice pathologies which are laryngitis, cyst, non-fluency syndrome, and dysphonia from the SVD dataset. The combination of specific 13 MFCC (mel-frequency cepstral coefficients) features along with pitch, zero crossing rate (ZCR), spectral flux, spectral entropy, spectral centroid, spectral roll-off, and short term energy for more accurate detection of voice pathologies. It is proven that the combination of features extracted gives the best product on the audio, which split into 10 ms. Four machine learning classifiers, SVM, Naïve Bayes, decision tree and ensemble classifier for the inter classifier comparison, give 93.18, 99.45,100 and 51%, respectively. Out of these accuracies, both Naïve Bayes and the decision tree show the most promising results with a higher detection rate. Naïve Bayes and decision tree gives the highest reported outcomes on the selected set of features in the proposed methodology. The SVM has also been concluded to be the commonly used voice condition identification algorithm.http://www.aimspress.com/article/doi/10.3934/mbe.2021114?viewType=HTMLvoice disordersvmnaïve bayesdecision treeensemblemfcc |
| spellingShingle | Sidra Abid Syed Munaf Rashid Samreen Hussain Anoshia Imtiaz Hamnah Abid Hira Zahid Inter classifier comparison to detect voice pathologies Mathematical Biosciences and Engineering voice disorder svm naïve bayes decision tree ensemble mfcc |
| title | Inter classifier comparison to detect voice pathologies |
| title_full | Inter classifier comparison to detect voice pathologies |
| title_fullStr | Inter classifier comparison to detect voice pathologies |
| title_full_unstemmed | Inter classifier comparison to detect voice pathologies |
| title_short | Inter classifier comparison to detect voice pathologies |
| title_sort | inter classifier comparison to detect voice pathologies |
| topic | voice disorder svm naïve bayes decision tree ensemble mfcc |
| url | http://www.aimspress.com/article/doi/10.3934/mbe.2021114?viewType=HTML |
| work_keys_str_mv | AT sidraabidsyed interclassifiercomparisontodetectvoicepathologies AT munafrashid interclassifiercomparisontodetectvoicepathologies AT samreenhussain interclassifiercomparisontodetectvoicepathologies AT anoshiaimtiaz interclassifiercomparisontodetectvoicepathologies AT hamnahabid interclassifiercomparisontodetectvoicepathologies AT hirazahid interclassifiercomparisontodetectvoicepathologies |