Advertisement

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

  • Émile Rocha Santana
    Correspondence
    Address correspondence and reprint requests to Émile Rocha Santana, Research conducted on the Graduate Program in Decision Models and Health of the Federal University of Paraíba (UFPB), João Pessoa, Paraíba, Brazil.
    Affiliations
    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
    Search for articles by this author
  • Leonardo Lopes
    Affiliations
    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
    Search for articles by this author
  • Ronei Marcos de Moraes
    Affiliations
    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
    Search for articles by this author
Published:November 11, 2022DOI:https://doi.org/10.1016/j.jvoice.2022.10.001

      Summary

      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.

      Key Words

      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Journal of Voice
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      REFERENCES

        • Teixeira LC
        • Behlau M.
        Comparison between vocal function exercises and voice amplification.
        J Voice. 2015; 29: 718-726https://doi.org/10.1016/j.jvoice.2014.12.012
        • Pedrosa V
        • Pontes A
        • Pontes P
        • et al.
        The effectiveness of the comprehensive voice rehabilitation program compared with the vocal function exercises method in behavioral dysphonia: a randomized clinical trial.
        J Voice. 2015; 30: 377https://doi.org/10.1016/j.jvoice.2015.03.013
        • Van Stan JH
        • Dijkers MP
        • Whyte J
        • et al.
        The rehabilitation treatment specification system: implications for improvements in research design, reporting, replication, and synthesis.
        Arch Phys Med Rehabil. 2019; 100: 146-155https://doi.org/10.1016/j.apmr.2018.09.112
        • Van Stan JH
        • Whyte J
        • Duffy JR
        • et al.
        Rehabilitation treatment specification system: methodology to identify and describe unique targets and ingredients.
        Arch Phys Med Rehabil. 2021; 102: 521-531https://doi.org/10.1016/j.apmr.2020.09.383
        • Van Stan JH
        • Roy N
        • Awan S
        • et al.
        A taxonomy of voice therapy.
        Am J Speech Lang Pathol. 2015; 24: 101-125https://doi.org/10.1044/2015_AJSLP-14-0030
        • Desjardins M
        • Halstead L
        • Cooke M
        • et al.
        A systematic review of voice therapy: what “effectiveness” really implies.
        J Voice. 2017; 31: 392
      1. National Center for Voice and Speech. Self-help for vocal health. Available at: http://ncvs.org/e-learning/strategies.html. Accessed June 6, 2009.

        • Ruotsalainen J
        • Sellman J
        • Lehto L
        Systematic review of the treatment of functional dysphonia and prevention of voice disorders.
        Otolaryngol Head Neck Surg. 2008; 138: 557-565https://doi.org/10.1016/j.otohns.2008.01.014
        • Theodoros DG
        • Ward EC.
        Intensive versus traditional voice therapy for vocal nodules: perceptual, physiological, acoustic and aerodynamic changes.
        J Voice. 2015; 29: 260
        • Behlau M
        • Pontes P
        • Vieira VP
        • et al.
        Presentation of the comprehensive vocal rehabilitation program for the treatment of behavioral dysphonia.
        CoDAS. 2013; 25: 492-496https://doi.org/10.1590/S2317-17822013000500015
        • Seipelt M
        • Nawka T
        • Gonnermann T
        • et al.
        Monitoring the outcome of phonosurgery and vocal exercises with established and new diagnostic tools.
        Biomed Res Int. 2020; 20: 01-10https://doi.org/10.1155/2020/4208189
        • Martins PC
        • Couto TE
        • Gama ACC.
        Auditory-perceptual evaluation of the degree of vocal deviation: correlation between the Visual Analogue Scale and Numerical Scale.
        CoDAS. 2015; 27: 279-284https://doi.org/10.1590/2317-1782/20152014167
        • Lopes LW
        • Sousa ESS
        • Silva ACF
        • et al.
        Cepstral measures in the assessment of severity of voice disorders.
        CoDAS. 2019; 31e20180175https://doi.org/10.1590/2317-1782/20182018175
        • Lv H
        • Tang H.
        Machine Learning methods and their application research.
        in: 2011 2nd International Symposium on Intelligence Information Processing and Trusted Computing. 2011,: 108-110https://doi.org/10.1109/IPTC.2011.34
        • Deng L
        • Dong Y.
        Deep learning: methods and applications.
        Found Trends Signal Process. 2014; 7: 197-387https://doi.org/10.1561/2000000039
        • Murphy KP.
        Machine Learning: A Probabilistic Perspective.
        MIT Press, 2012 (Accessed 07 September 2022)
        • Hegde S.
        • Shetty S
        • Rai S
        • et al.
        A survey on machine learning approaches for automatic detection of voice disorders.
        J Voice. 2019; 33: 947https://doi.org/10.1016/j.jvoice.2018.07.014
        • Moraes RM
        • Silva ILA
        • Machado LS.
        Online skills assessment in training based on virtual reality using a novel fuzzy triangular naive bayes network.
        in: 14th International FLINS Conference on Robotics and Artificial Intelligence (FLINS 2020). 18-21 Agosto, Colônia, Alemanha. 2020: 446-454https://doi.org/10.1142/9789811223334_0054
        • Barros LC
        • Esmi E.
        Notas sobre Fuzzy x Probabilidades.
        CBFS. 2016;
        • Kentel E
        • Aral MM.
        Modelagem de risco de saúde probabilístico-fuzzy.
        Stoch Envir Res e Risk Ass. 2004; 18: 324-338https://doi.org/10.1007/s00477-004-0187-3
        • Silva NFC
        • Vianna CMM
        • Oliveira FSG
        • et al.
        Fuzzy Visa: um modelo de lógica fuzzy para a avaliação de risco da Vigilância Sanitária para inspeção de resíduos de serviços de saúde.
        Physis Revista de Saúde Coletiva. 2017; 27: 127-146https://doi.org/10.1590/S0103-73312017000100007
        • Soria D
        • Garibaldi JM
        • Ambrogi F
        • et al.
        A ”non-parametric” version of the naive Bayes classifier.
        Knowl-Based Syst. 2011; 24: 775-784https://doi.org/10.1016/j.knosys.2011.02.014
        • Lopes L.
        Por dentro da estatística Características das variáveis e a aplicação dos testes estatísticos.
        Einstein: Educ Contin Saúde. 2009; 7: 121-122
        • Bonette MC
        • Ribeiro VV
        • Xavier-Fadel CB
        • et al.
        Immediate effect of semioccluded vocal tract exercises using resonance tube phonation in water on women without vocal complaints.
        J Voice. 2020; 34: 962https://doi.org/10.1016/j.jvoice.2019.06.02
        • Grady M
        • Cook-Cunningham SL.
        The effects of three physical and vocal warm-up procedures on acoustic and perceptual measures of choral sound: study replication with younger populations.
        J Voice. 2018; 32: 192-199https://doi.org/10.1016/j.jvoice.2017.04.003
        • Kaneko M
        • Hirano S
        • Tateya I
        • et al.
        Multidimensional analysis on the effect of vocal function exercises on aged vocal fold atrophy.
        J Voice. 2015; 29: 638-644https://doi.org/10.1016/j.jvoice.2014.10.017
        • Pereira EC
        • Silvério KCA
        • Marques JM
        • et al.
        Immediate effect of vocal techniques in women without vocal complaint.
        Rev.CEFAC. 2011; 13: 886-894https://doi.org/10.1590/S1516-18462011005000061
        • Patel RR
        • Awan NS
        • Barkmeier-Kraemer J
        • et al.
        Recommended protocols for instrumental assessment of voice: American Speech-Language-Hearing Association expert panel to develop a protocol for instrumental assessment of vocal function.
        Am J Speech Lang Pathol. 2018; 6 (27): 887-905https://doi.org/10.1044/2018_AJSLP- 17-0009
        • Lopes LW
        • Alves JN
        • Evangelista DS
        • et al.
        Accuracy of traditional and formant acoustic measurements in the evaluation of vocal quality.
        CoDAS. 2018; 30e20170282https://doi.org/10.1590/2317-1782/20182017282
      2. Conserva KCF. Efeito Imediato dos Exercícios Vocais sobre as medidas de Fonte e Filtro. Dissertação de Doutorado. Programa de Pós-Graduação em Linguística. Universidade Federal da Paraíba (UFPB), 2019.

      3. Géron A. Mãos à Obra: Aprendizado de Máquina com Scikit-Learn & TensorFlow. [S.l.]: Alta Books, 2019. ISBN 9788550809021.

      4. Igual L, Seguí S. Introduction to data science: apython approach to concepts, techniques and applications.: Springer International Publishing, 2017. (Undergraduate Topics in Computer Science). ISBN 9783319500171

        • Bossuyt PM.
        Clinical evaluation of medical tests: still a long road to go.
        Biochem Med (Zagreb). 2006; 16: 103-106https://doi.org/10.11613/BM.2006.010
        • Perroca MG
        • Gaidzinski RR.
        Assessing the interrater reliability of an instrument for classifying patients: kappa quotient.
        Rev Esc Enferm USP. 2003; 37: 72-80https://doi.org/10.1590/S0080-62342003000100009
        • Landis JR
        • Koch GG.
        The measurement of observer agreement for categorical data.
        Biometrics. 1977; 33: 159-174
        • Lopes L
        • Vieira V
        • Behlau M.
        Performance of different acoustic measures to discriminate individuals with and without voice disorders.
        J Voice. 2020; (S0892-1997(20)30258-7)https://doi.org/10.1016/j.jvoice.2020.07.008
        • Behlau M
        • Madazio G
        • Pontes P.
        Disfonias organofuncionais. In: Behlau M. Voz -O livro do especialista.
        Rio de Janeiro: Revinter;. 2001; : 295-341
        • Silva FC
        • Ramos LA
        • Souza BO
        • et al.
        Ideal time of sonorous tongue vibration of dysphonic children.
        Distúrb Comun. 2017; 29: 673-682https://doi.org/10.23925/2176-2724.2017v29i4p673-682
      5. Baravieira PB. Aplicação de uma rede neural artificial para a avaliação da rugosidade e soprosidade. 2016. 101f. Tese (Doutorado) - Programa de Pós- Graduação Interunidades em Bioengenharia EESC/FMRP/IQSC, Universidade de São Paulo, 2016.

        • Sáenz-Lechón N.
        • Fraile R
        • Godino-Llorente JI
        • et al.
        Towards objective evaluation of perceived roughness and breathiness: an approach based on mel-frequency cepstral analysis.
        Logoped Phoniatr Vocol. 2011; 36: 52-59https://doi.org/10.3109/14015439.2010.517551
        • Moro-Velázquez L.
        • Gómez-García JA
        • Godino-Llorente JI
        • et al.
        Modulation spectra morphological parameters: a new method to assess voice pathologies according to the GRBAS scale.
        Biomed Res Int. 2015; 2015259239https://doi.org/10.1155/2015/259239
        • Uloza V
        • Verikas A
        • Bacauskiene M
        • et al.
        Categorizing normal and pathological voices: automated and perceptual categorization.
        J Voice. 2011; 25: 700-708https://doi.org/10.1016/j.jvoice.2010.04.009
        • Godino-Llorente JI
        • Gomez-Vilda P.
        Automatic detection of voice impairments by means of short-term cepstral parameters and neural network based detectors.
        IEEE Trans Biomed Eng. 2004; 51: 380-384https://doi.org/10.1109/TBME.2003.820386
        • Titze IR.
        Voice training and therapy with a semioccluded vocal tract: rationale and scientific underpinnings.
        J Speech Lang Hear Res. 2006; 49: 448-459https://doi.org/10.1044/1092-4388(2006/035)
        • Titze I.
        Phonation threshold pressure measurement with a semi-occluded vocal tract.
        J Speech Lang Hear Res. 2009; 52: 1062-1072https://doi.org/10.1044/1092-4388(2009/08-0110
        • Costa CB
        • Costa LHC
        • Oliveira G
        • et al.
        Immediate effects of the phonation into a straw exercise.
        Braz J Otorhinolaryngol. 2011; 77: 461-465https://doi.org/10.1590/S1808-86942011000400009
      6. Nalesso KS. Efeito terapêutico do uso exclusivo do tubo de ressonância flexível na região glótica e no trato vocal supraglótico. Dissertação de mestrado - Universidade Estadual de Campinas, Faculdade de Ciências Médicas. 2015.

        • Kawamura T.
        Interpretação de um Teste sob a Visão Epidemiológica. Eficiência de um Teste.
        Arq Bras Cardiol. 2002; 79: 437-444https://doi.org/10.1590/S0066-782X2002001300015
      7. Pinho SMR. Fundamentos em Fonoaudiologia. Tratando os Distúrbios da Voz. Guanabara Koogan; 1998. 125

        • Menezes MH
        • Ubrig-Zancanella MT
        • Cunha MGB
        • et al.
        The relationship between tongue trill performance duration and vocal changes in dysphonic women.
        J Voice. 2011; 25: e167-e175https://doi.org/10.1016/j.jvoice.2010.03.009
        • Schwarz K
        • Cielo CA.
        Vocal and laryngeal modifications produced by the sonorous tongue vibration technique.
        Pró-Fono Revista de Atualização Científica. 2009; 21: 161-166https://doi.org/10.1590/s0104-56872009000200013
      8. Cunha MG, Pacheco COLC, Menezes MHM, et al. A eficácia da vibração sonorizada de língua e da emissão do som nasal /m/em pacientes com nódulos de pregas vocais: Estudo comparativo. Anais do XII congresso brasileiro de fonoaudiologia, Santos - São Paulo; 2005. 27.

        • Menezes MHM
        • Duprat AC
        • Costa HO
        Vocal and laryngeal effects of voiced tongue vibration technique according to performance time.
        J Voice. 2005; 19: 61-70https://doi.org/10.1016/j.jvoice.2003.11.002
        • Bento FAM
        • Diaféria GLA
        • Fonoff ET
        • et al.
        Effect of overarticulation technique in voice and speech of individuals with Parkinson’s disease with deep brain stimulation.
        Audiol Commun Res. 2019; 24: e2008https://doi.org/10.1590/2317-6431-2018-2008
        • Van Lierde KMV
        • D’haeseleer E
        • Baudonck N
        • et al.
        The impact of vocal warm-up exercises on the objective vocal quality in female students training to be speech language pathologists.
        J Voice. 2011; 25: e115-e121https://doi.org/10.1016/j.jvoice.2009.11.004