Recognition of the Effect of Vocal Exercises by Fuzzy Triangular Naive Bayes, a Machine Learning Classifier: A Preliminary Analysis

Émile Rocha Santana; Leonardo Lopes; Ronei Marcos de Moraes

doi:10.1016/j.jvoice.2022.10.001

Recognition of the Effect of Vocal Exercises by Fuzzy Triangular Naive Bayes, a Machine Learning Classifier: A Preliminary Analysis

J Voice. 2022 Nov 11:S0892-1997(22)00307-1. doi: 10.1016/j.jvoice.2022.10.001. Online ahead of print.

Authors

Émile Rocha Santana¹, Leonardo Lopes², Ronei Marcos de Moraes³

Affiliations

¹ Department of Life Sciences, Collegiate of Speech Language and Hearing Sciences, State University of Bahia, UNEB, Departamento de Ciências da Vida I, Colegiado de Fonoaudiologia. Salvador 41150-000, Bahia, Brazil; Department of Statistics, Graduate Program in Decision Models and Health of the Federal University of Paraíba (UFPB), Campus I, Centro de Ciências Exatas e da Natureza, Departamento de Ciências Exatas. João Pessoa 58051-900, Paraíba, Brazil. Electronic address: emile.fono@gmail.com.
² Department of Speech Therapy, Federal University of Paraíba, UFPB, Campus I, Centro de Ciências da Saúde, Departamento de Fonoaudiologia, Cidade Universitária, João Pessoa 58051-900, Paraíba, Brazil. Electronic address: lwlopes@hotmail.com.
³ Department of Statistics, Graduate Program in Decision Models and Health of the Federal University of Paraíba (UFPB), Campus I, Centro de Ciências Exatas e da Natureza, Departamento de Ciências Exatas. João Pessoa 58051-900, Paraíba, Brazil. Electronic address: ronei@de.ufpb.br.

PMID: 36376192
DOI: 10.1016/j.jvoice.2022.10.001

Abstract

Objectives: Machine learning (ML) methods allow the development of expert systems for pattern recognition and predictive analysis of intervention outcomes. It has been used in Voice Sciences, mainly to discriminate between healthy and dysphonic voices. Parameter patterns of vocal acoustic analysis and vocal perceptual assessment can be evaluated by ML classifiers, such as the Fuzzy Triangular Naive Bayes (FTriangNB), after using techniques that improve the vocal quality of individuals with healthy or dysphonic voices. Thus, the goal of this study was to analyze the performance of the FTriangNB to detect patterns in the acoustic parameters and the auditory-perceptual assessment of 12 women with dysphonia and 12 vocally healthy women, after performing three vocal exercises (tongue trills, semi-occluded vocal tract exercise with a high-resistance straw - SOVTE, and over-articulation).

Methods: The FTriangNB classifier contained in the Fuzzy Class package was implemented in the data analysis software R Studio version 1.4.1106 for Macintosh. The confusion matrix was extracted, as well as the accuracy, the Kappa coefficient, and the class statistics. The final result was compared with those generated by FTriangNB with the same variables from the preapplication database of the exercises.

Results: The FTriangNB presented good accuracy (87.5%) and Kappa coefficient (81.3%), and showed almost perfect agreement after application of the exercises, while the results before the application of the exercises demonstrated accuracy without acceptable discrimination capacity (33.3%) and Kappa coefficient with a poor agreement (-6.67%). The Semioccluded Vocal Tract Exercises (SOVTE) with high strength straw presented with a sensitivity and Negative Predictive Value (NPV) of value 1 (one), and the over-articulation's specificity and Positive Predictive Value (PPV) also showed a value of 1 (one).

Conclusions: The FTriangNB showed great accuracy in recognizing the effect of vocal exercises. Exploratory studies with larger samples using FTriangNB, as well as other Machine Learning classifiers should be further carried out for this purpose in the Voice Science to enable inferences.

Keywords: Fuzzy classification; Machine learning (ML); Naive bayes network; Triangular distribution; Vocal training; Voice assessment.