A hybrid approach for binary and multi-class classification of voice disorders using a pre-trained model and ensemble classifiers

Abstract Recent advances in artificial intelligence-based audio and speech processing have increasingly focused on the binary and multi-class classification of voice disorders. Despite progress, achieving high accuracy in multi-class classification remains challenging. This paper proposes a novel hy...

Full description

Saved in:
Bibliographic Details
Main Authors: Mehtab Ur Rahman, Cem Direkoglu
Format: Article
Language:English
Published: BMC 2025-05-01
Series:BMC Medical Informatics and Decision Making
Subjects:
Online Access:https://doi.org/10.1186/s12911-025-02978-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849314734462992384
author Mehtab Ur Rahman
Cem Direkoglu
author_facet Mehtab Ur Rahman
Cem Direkoglu
author_sort Mehtab Ur Rahman
collection DOAJ
description Abstract Recent advances in artificial intelligence-based audio and speech processing have increasingly focused on the binary and multi-class classification of voice disorders. Despite progress, achieving high accuracy in multi-class classification remains challenging. This paper proposes a novel hybrid approach using a two-stage framework to enhance voice disorders classification performance, and achieve state-of-the-art accuracies in multi-class classification. Our hybrid approach, combines deep learning features with various powerful classifiers. In the first stage, high-level feature embeddings are extracted from voice data spectrograms using a pre-trained VGGish model. In the second stage, these embeddings are used as input to four different classifiers: Support Vector Machine (SVM), Logistic Regression (LR), Multi-Layer Perceptron (MLP), and an Ensemble Classifier (EC). Experiments are conducted on a subset of the Saarbruecken Voice Database (SVD) for male, female, and combined speakers. For binary classification, VGGish-SVM achieved the highest accuracy for male speakers (82.45% for healthy vs. disordered; 75.45% for hyperfunctional dysphonia vs. vocal fold paresis), while VGGish-EC performed best for female speakers (71.54% for healthy vs. disordered; 68.42% for hyperfunctional dysphonia vs. vocal fold paresis). In multi-class classification, VGGish-SVM outperformed other models, achieving mean accuracies of 77.81% for male speakers, 63.11% for female speakers, and 70.53% for combined genders. We conducted a comparative analysis against related works, including the Mel frequency cepstral coefficient (MFCC), MFCC-glottal features, and features extracted using the wav2vec and HuBERT models with SVM classifier. Results demonstrate that our hybrid approach consistently outperforms these models, especially in multi-class classification tasks. The results show the feasibility of a hybrid framework for voice disorder classification, offering a foundation for refining automated tools that could support clinical assessments with further validation.
format Article
id doaj-art-e51a30b85c28413ea96794fd268f3b58
institution Kabale University
issn 1472-6947
language English
publishDate 2025-05-01
publisher BMC
record_format Article
series BMC Medical Informatics and Decision Making
spelling doaj-art-e51a30b85c28413ea96794fd268f3b582025-08-20T03:52:23ZengBMCBMC Medical Informatics and Decision Making1472-69472025-05-0125111410.1186/s12911-025-02978-wA hybrid approach for binary and multi-class classification of voice disorders using a pre-trained model and ensemble classifiersMehtab Ur Rahman0Cem Direkoglu1Department of Language and Communication, Radboud UniversityElectrical and Electronics Engineering Department, Middle East Technical UniversityAbstract Recent advances in artificial intelligence-based audio and speech processing have increasingly focused on the binary and multi-class classification of voice disorders. Despite progress, achieving high accuracy in multi-class classification remains challenging. This paper proposes a novel hybrid approach using a two-stage framework to enhance voice disorders classification performance, and achieve state-of-the-art accuracies in multi-class classification. Our hybrid approach, combines deep learning features with various powerful classifiers. In the first stage, high-level feature embeddings are extracted from voice data spectrograms using a pre-trained VGGish model. In the second stage, these embeddings are used as input to four different classifiers: Support Vector Machine (SVM), Logistic Regression (LR), Multi-Layer Perceptron (MLP), and an Ensemble Classifier (EC). Experiments are conducted on a subset of the Saarbruecken Voice Database (SVD) for male, female, and combined speakers. For binary classification, VGGish-SVM achieved the highest accuracy for male speakers (82.45% for healthy vs. disordered; 75.45% for hyperfunctional dysphonia vs. vocal fold paresis), while VGGish-EC performed best for female speakers (71.54% for healthy vs. disordered; 68.42% for hyperfunctional dysphonia vs. vocal fold paresis). In multi-class classification, VGGish-SVM outperformed other models, achieving mean accuracies of 77.81% for male speakers, 63.11% for female speakers, and 70.53% for combined genders. We conducted a comparative analysis against related works, including the Mel frequency cepstral coefficient (MFCC), MFCC-glottal features, and features extracted using the wav2vec and HuBERT models with SVM classifier. Results demonstrate that our hybrid approach consistently outperforms these models, especially in multi-class classification tasks. The results show the feasibility of a hybrid framework for voice disorder classification, offering a foundation for refining automated tools that could support clinical assessments with further validation.https://doi.org/10.1186/s12911-025-02978-wVoice disordersMulti-class classificationEnsemble classifierVGGish
spellingShingle Mehtab Ur Rahman
Cem Direkoglu
A hybrid approach for binary and multi-class classification of voice disorders using a pre-trained model and ensemble classifiers
BMC Medical Informatics and Decision Making
Voice disorders
Multi-class classification
Ensemble classifier
VGGish
title A hybrid approach for binary and multi-class classification of voice disorders using a pre-trained model and ensemble classifiers
title_full A hybrid approach for binary and multi-class classification of voice disorders using a pre-trained model and ensemble classifiers
title_fullStr A hybrid approach for binary and multi-class classification of voice disorders using a pre-trained model and ensemble classifiers
title_full_unstemmed A hybrid approach for binary and multi-class classification of voice disorders using a pre-trained model and ensemble classifiers
title_short A hybrid approach for binary and multi-class classification of voice disorders using a pre-trained model and ensemble classifiers
title_sort hybrid approach for binary and multi class classification of voice disorders using a pre trained model and ensemble classifiers
topic Voice disorders
Multi-class classification
Ensemble classifier
VGGish
url https://doi.org/10.1186/s12911-025-02978-w
work_keys_str_mv AT mehtaburrahman ahybridapproachforbinaryandmulticlassclassificationofvoicedisordersusingapretrainedmodelandensembleclassifiers
AT cemdirekoglu ahybridapproachforbinaryandmulticlassclassificationofvoicedisordersusingapretrainedmodelandensembleclassifiers
AT mehtaburrahman hybridapproachforbinaryandmulticlassclassificationofvoicedisordersusingapretrainedmodelandensembleclassifiers
AT cemdirekoglu hybridapproachforbinaryandmulticlassclassificationofvoicedisordersusingapretrainedmodelandensembleclassifiers