Integrating binary classification and clustering for multi-class dysarthria severity level classification: a two-stage approach
Authors: 
Afnan S. Al-Ali, Raseena M. Haris, Younes Akbari, Moutaz Saleh, Somaya Al-Maadeed, M. Rajesh KumarAuthors Info & Claims
Afnan S. Al-Ali, Raseena M. Haris, Younes Akbari, Moutaz Saleh, Somaya Al-Maadeed, M. Rajesh KumarAuthors Info & ClaimsAbstract
Dysarthria, a motor speech disorder, poses challenges in accurate severity assessment. Recent research has excelled in classifying dysarthria based on severity levels, primarily utilizing annotated datasets and achieving high accuracies. However, these classification-based approaches may not readily translate to real-world scenarios without predefined labels. This study follows a different path by proposing a two-stage approach leveraging binary classification and clustering to comprehensively analyze and classify dysarthria severity levels. We begin by employing binary classification to differentiate control from dysarthric cases by experiencing eight different feature extraction techniques and two classifiers in order to support the largest amount of dysarthric cases to the second stage, where k-means clustering uncovers hidden patterns and boundaries within dysarthria severity levels, enabling a more nuanced understanding of the disorder. We applied our methodology to the TORGO dataset, a benchmark in dysarthria research, and evaluated it on the UA Speech dataset. After optimizing the number of clusters, our approach achieved an accuracy of 91% with sentence-based features and 85% with word-based features in clustering. This research extends previous studies by exploring unsupervised clustering to differentiate severity levels in unannotated cases, bridging the gap between controlled datasets and practical applications. Our findings highlight the effectiveness of clustering-driven two-stage analysis in improving dysarthria severity-level classification, with implications for real-world clinical settings.
References
[1]
Lanier W Speech Disorders 2010 London Greenhaven Publishing LLC
[2]
Morley, M., Court, D., Miller, H.: The American heritage dictionary entry: dysarthria. www.ahdictionary.com. Retrieved 2020-03-07
[3]
Duffy J Functional speech disorders: clinical manifestations, diagnosis, and management Handb. Clin. Neurol. 2016 139 379-388
[4]
Morley M, Court D, and Miller H Developmental dysarthria Br. Med. J. 1954 1 4852 8
[5]
Enderby P Disorders of communication: dysarthria Handb. Clin. Neurol. 2013 110 273-281
[6]
Zyski BJ and Weisiger BE Identification of dysarthria types based on perceptual analysis J. Commun. Disord. 1987 20 5 367-378
[7]
Hernandez A, Kim S, and Chung M Prosody-based measures for automatic severity assessment of dysarthric speech Appl. Sci. 2020 10 19 6999
[8]
Al-Qatab BA and Mustafa MB Classification of dysarthric speech according to the severity of impairment: an analysis of acoustic features IEEE Access 2021 9 18183-18194
[9]
Joshy AA and Rajan R Dysarthria severity assessment using squeeze-and-excitation networks Biomed. Signal Process. Control 2023 82
[10]
Gupta S, Patil AT, Purohit M, Parmar M, Patel M, Patil HA, and Guido RC Residual neural network precisely quantifies dysarthria severity-level based on short-duration speech segments Neural Netw. 2021 139 105-117
[11]
Zhou Q, Yuan Y, Lu H, Li X, Liu Z, Gan J, Yue Z, Wu J, Sheng J, and Xin L Cancer functional states-based molecular subtypes of gastric cancer J. Transl. Med. 2023 21 1 1-15
[12]
Lukauskas M and Ruzgas T Data clustering and its applications in medicine New Trends Math. Sci. ISAME 2022 Proc. 2022 10 1 67-70
[13]
Al-Ali, A., Al-Maadeed, S., Saleh, M., Naidu, R.C., Alex, Z.C., Ramachandran, P., Khoodeeram, R., et al.: Classification of dysarthria based on the levels of severity. A systematic review. Preprint arXiv:2310.07264 (2023)
[14]
Joshy, A.A., Rajan, R.: Automated dysarthria severity classification using deep learning frameworks. In: 2020 28th European Signal Processing Conference (EUSIPCO), pp. 116–120. IEEE (2021)
[15]
Joshy AA and Rajan R Automated dysarthria severity classification: a study on acoustic features and deep learning techniques IEEE Trans. Neural Syst. Rehabil. Eng. 2022 30 1147-1157
[16]
Hernandez, A., Yeo, E.J., Kim, S., Chung, M.: Dysarthria detection and severity assessment using rhythm-based metrics. In: INTERSPEECH, pp. 2897–2901 (2020)
[17]
Chandrashekar, H., Karjigi, V., Sreedevi, N.: Breathiness indices for classification of dysarthria based on type and speech intelligibility. In: 2019 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET), pp. 266–270. IEEE (2019)
[18]
Karjigi V and Sreedevi N Speech intelligibility assessment of dysarthria using fisher vector encoding Comput. Speech Lang. 2023 77
[19]
Bhat, C., Vachhani, B., Kopparapu, S.K.: Automatic assessment of dysarthria severity level using audio descriptors. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5070–5074 (2017). IEEE
[20]
Yeo, E.J., Choi, K., Kim, S., Chung, M.: Cross-lingual dysarthria severity classification for English, Korean, and Tamil. In: 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 566–574. IEEE (2022)
[21]
Rudzicz F, Namasivayam AK, and Wolff T The Torgo database of acoustic and articulatory speech from speakers with dysarthria Lang. Resour. Eval. 2012 46 523-541
[22]
Kim, H., Hasegawa-Johnson, M., Perlman, A., Gunderson, J., Huang, T.S., Watkin, K., Frame, S.: Dysarthric speech database for universal access research. In: Ninth Annual Conference of the International Speech Communication Association (2008)
[23]
Meyer D and Wien F Support vector machines Interface Libsvm Pack. e1071 2015 28 20 597
[24]
Rodríguez-Pérez R and Bajorath J Evolution of support vector machine and regression modeling in chemoinformatics and drug discovery J. Comput. Aided Mol. Des. 2022 36 5 355-362
[25]
Pontil M and Verri A Properties of support vector machines Neural Comput. 1998 10 4 955-974
[26]
Vyas, G., Dutta, M.K., Prinosil, J., Harár, P.: An automatic diagnosis and assessment of dysarthric speech using speech disorder specific prosodic features. In: 2016 39th International Conference on Telecommunications and Signal Processing (TSP), pp. 515–518. IEEE (2016)
[27]
Kim, M.J., Yoo, J., Kim, H.: Dysarthric speech recognition using dysarthria-severity-dependent and speaker-adaptive models. In: Interspeech, pp. 3622–3626 (2013)
[28]
Abdolrasol MG, Hussain SS, Ustun TS, Sarker MR, Hannan MA, Mohamed R, Ali JA, Mekhilef S, and Milad A Artificial neural networks based optimization techniques: a review Electronics 2021 10 21 2689
[29]
Ghiassi M and Saidane H A dynamic architecture for artificial neural networks Neurocomputing 2005 63 397-413
[30]
Mitra V and Wang C-J Content based audio classification: a neural network approach Soft. Comput. 2008 12 639-646
[31]
Mendez KM, Reinke SN, and Broadhurst DI A comparative evaluation of the generalised predictive ability of eight machine learning algorithms across ten clinical metabolomics data sets for binary classification Metabolomics 2019 15 1-15
[32]
Madhulatha, T.S.: An overview on clustering methods. Preprint arXiv:1205.1117 (2012)
[33]
Arabie P, Hubert L, and De Soete G Clustering and Classification 1996 Singapore World Scientific
[34]
Alashwal H, El Halaby M, Crouse JJ, Abdalla A, and Moustafa AA The application of unsupervised clustering methods to Alzheimer’s disease Front. Comput. Neurosci. 2019 13 31
[35]
Murtagh F and Contreras P Algorithms for hierarchical clustering: an overview Wiley Interdiscip. Rev. Data Min. Knowl. Disc. 2012 2 1 86-97
[36]
Liu Q, Deng M, Shi Y, and Wang J A density-based spatial clustering algorithm considering both spatial proximity and attribute similarity Comput. Geosci. 2012 46 296-309
[37]
Derpanis KG Mean shift clustering Lect. Notes 2005 32 1-4
[38]
Müllner, D.: Modern hierarchical, agglomerative clustering algorithms. Preprint arXiv:1109.2378 (2011)
[39]
Swarndeep Saket J and Pandya S An overview of partitioning algorithms in clustering techniques Int. J. Adv. Res. Comput. Eng. Technol. (IJARCET) 2016 5 6 1943-1946
[40]
Hartigan JA and Wong MA Algorithm as 136: a k-means clustering algorithm J. R. Stat. Soc. Ser. C (Appl. Stat.) 1979 28 1 100-108
[41]
Qi Y Random forest for bioinformatics Ensemb. Mach. Learn. Methods Appl. 2012 2012 307-323
[42]
Joshy, A.A., Parameswaran, P., Nair, S.R., Rajan, R.: Statistical analysis of speech disorder specific features to characterise dysarthria severity level. In: ICASSP 2023–2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1–5. IEEE (2023)
[43]
Thorndike RL Who belongs in the family? Psychometrika 1953 18 4 267-276
[44]
Rousseeuw PJ Silhouettes: a graphical aid to the interpretation and validation of cluster analysis J. Comput. Appl. Math. 1987 20 53-65
[45]
Davies DL and Bouldin DW A cluster separation measure IEEE Trans. Pattern Anal. Mach. Intell. 1979 2 224-227
[46]
Tripathi, A., Bhosale, S., Kopparapu, S.K.: Improved speaker independent dysarthria intelligibility classification using deep speech posteriors. In: ICASSP 2020–2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6114–6118. IEEE (2020)
[47]
Chandrashekar H, Karjigi V, and Sreedevi N Spectro-temporal representation of speech for intelligibility assessment of dysarthria IEEE J. Sel. Top. Signal Process. 2019 14 2 390-399
[48]
Gurugubelli, K., Vuppala, A.K.: Perceptually enhanced single frequency filtering for dysarthric speech detection and intelligibility assessment. In: ICASSP 2019–2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6410–6414. IEEE (2019)
Index Terms
- Integrating binary classification and clustering for multi-class dysarthria severity level classification: a two-stage approach
Index terms have been assigned to the content through auto-classification.
Recommendations
Significance of Energy Features for Severity Classification of Dysarthria
Speech and ComputerAbstractDysarthria is a neuro-motor speech disorder that affects the intelligibility of speech, which is often imperceptible depending on its severity-level. Patients’ advancement in the dysarthric severity-level are diagnosed using the classification ...
Continuous Wavelet Transform for Severity-Level Classification of Dysarthria
Speech and ComputerAbstractDysarthria is a neuro-motor speech defect that causes speech to be unintelligible and is largely unnoticeable to humans at various severity-levels. Dysarthric speech classification is used as a diagnostic method to assess the progression of a ...
Pre-trained models for detection and severity level classification of dysarthria from speech
AbstractAutomatic detection and severity level classification of dysarthria from speech enables non-invasive and effective diagnosis that helps clinical decisions about medication and therapy of patients. In this work, three pre-trained models (wav2vec2-...
Highlights- Layer-wise analysis of pre-trained models for detection of dysarthria.
- Layer-wise analysis of pre-trained models for severity level classification.
- Systematic comparison of conventional features and pre-trained model embeddings.
Comments
Information & Contributors
Information
Published In
© The Author(s) 2024.
Publisher
Kluwer Academic Publishers
United States
Publication History
Published: 27 November 2024
Accepted: 17 August 2024
Revision received: 12 August 2024
Received: 12 February 2024
Author Tags
Qualifiers
- Research-article
Funding Sources
- Qatar University
- Qatar University
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 08 Feb 2025