CoDAS
https://codas.org.br/article/doi/10.1590/2317-1782/e20250288pt
CoDAS
Artigo Original

Acurácia e ponto de corte de diferentes medidas acústicas na tarefa de vogal sustentada em falantes do português brasileiro

Accuracy and cut-off values of different acoustic measures in the sustained vowel task of Brazilian Portuguese speakers

Amanda Feliciano; Mara Behlau; Jordana Balbinot; Samuel Ribeiro de Abreu; Vanessa Veis Ribeiro; Leonardo Wanderley Lopes

Downloads: 0
Views: 1

Resumo

Objetivo: Definir os valores de corte das medidas acústicas extraídas da tarefa de vogal sustentada [a] para discriminação entre presença e ausência de distúrbio vocal em falantes do português brasileiro. Método: A amostra foi composta por 376 participantes, 288 do gênero feminino e 88 do gênero masculino, com idade média de 41,20 ± 14,04 anos. Os indivíduos foram submetidos ao exame de avaliação laringológica, e a uma gravação vocal, sendo coletada uma amostra de fala com a vogal [a] sustentada e posteriormente realizado o julgamento perceptivo auditivo e acústico da voz, dos quais 277 foram classificados com distúrbio vocal e 99 sem distúrbio vocal. Foram extraídas 44 medidas acústicas e analisadas por meio da curva ROC para identificação do ponto de corte de cada medida, bem como suas métricas de desempenho. Resultados: Foram definidos pontos de corte para 23 das 44 medidas acústicas inicialmente extraídas. Dentre elas, seis medidas demonstraram desempenho robusto e clinicamente relevante para discriminar vozes com e sem distúrbio vocal em falantes do português brasileiro. As medidas com valores de AUC superiores a 0,70 e sensibilidade e especificidade equilibradas acima de 70% foram: Amplitude Variability Index (AVI) (≤0,91), Glottal-to-noise excitation (GNE)2000Hz (>0,92), Spectral Noise Level (SNL)100-2600Hz (≤7,71), SNL100-3000Hz (≤3,38), SNL100-8000Hz (≤10,95) e SNL5100-8000Hz (≤–1,84). Conclusão: Seis medidas apresentaram desempenho satisfatório para identificar a presença de distúrbio vocal em falantes do português brasileiro. Dez medidas apresentaram bom desempenho para triagem vocal e sete para confirmação diagnóstica de distúrbio vocal.

Palavras-chave

Voz; Acústica; Distúrbios da Voz; Disfonia; Diagnóstico

Abstract

Purpose: To define cut-off values for acoustic measures extracted from the sustained vowel [a] task to discriminate between the presence and absence of vocal disorders in Brazilian Portuguese speakers. Methods: The sample consisted of 376 participants, 288 female and 88 male, with a mean age of 41.20 ± 14.04 years. All individuals underwent a laryngological evaluation and a voice recording session, during which a sustained vowel [a] sample was collected. Subsequently both auditory-perceptual and acoustic analyses of the voice were performed. Among the participants 277 were classified as having a vocal disorder and 99 as having no vocal disorder. A total of 44 acoustic measures were extracted and analyzed using ROC curves to determine the cut-off value for each measure, along with their performance metrics (sensitivity, specificity and AUC). Results: Cut-off values were established for 23 of the 44 extracted acoustic measures. Six measures showed robust and clinically relevant performance in discriminating between voices with and without vocal disorders in Brazilian Portuguese speakers. The measures with AUC values greater than 0.70 and balanced sensitivity and specificity above 70% were: Amplitude Variability Index (AVI) (≤0,91), Glottal-to-noise excitation (GNE)2000Hz (>0,92), Spectral Noise Level (SNL)100-2600Hz (≤7,71), SNL100-3000Hz (≤3,38), SNL100-8000Hz (≤10,95) and SNL5100-8000Hz (≤–1,84). Conclusion: Six acoustic measures demonstrated satisfactory performance in identifying the presence of vocal disorders in Brazilian Portuguese speakers. Ten measures showed good performance for voice screening purposes and seven for diagnostic confirmation of vocal disorders.

Keywords

Voice; Acoustic; Voice Disorders; Dysphonia; Diagnostic

Referências

  • Englert M, Lopes L, Vieira V, Behlau M. Accuracy of Acoustic Voice Quality Index and its isolated acoustic measures to discriminate the severity of voice disorders. J Voice. 2022;36(4):582.e1-10. https://doi.org/10.1016/j.jvoice.2020.08.010 PMid:32873433.
    » https://doi.org/10.1016/j.jvoice.2020.08.010
  • 2Jalali‑najafabadi F, Gadepalli C, Jarchi D, Cheetham BMG. Acoustic analysis and digital signal processing for the assessment of voice quality. Biomed Signal Process Control. 2021;70:103018. https://doi.org/10.1016/j.bspc.2021.103018
    » https://doi.org/10.1016/j.bspc.2021.103018
  • 3Lopes LW, Alves JN, Evangelista DS, França FP, Vieira VJD, Lima-Silva MFB, et al. Acurácia das medidas acústicas tradicionais e formânticas na avaliação da qualidade vocal. CoDAS. 2018;30(5):e20170282. https://doi.org/10.1590/2317-1782/20182017282 PMid:30365651.
    » https://doi.org/10.1590/2317-1782/20182017282
  • 4Uloza V, Pribuišis K, Ulozaite-Stanienė N, Petrauskas T, Damaševičius R, Maskeliūnas R. Accuracy analysis of the multiparametric acoustic voice indices, the VWI, AVQI, ABI, and DSI measures, in differentiating between normal and dysphonic voices. J Clin Med. 2023;13(1):99. https://doi.org/10.3390/jcm13010099 PMid:38202106.
    » https://doi.org/10.3390/jcm13010099
  • 5Nascimento RCPB, Sampaio MC. Os efeitos do gênero e da idade nas medidas acústicas tradicionais e cepstrais em vozes saudáveis e disfônicas: revisão de literatura sistemática [trabalho de conclusão de curso]. Salvador: Departamento de Fonoaudiologia, Universidade Federal da Bahia; 2022.
  • 6Lopes LW, Abreu SR. Accuracy and cut-off values of cepstral measures in the clinical evaluation of Brazilian Portuguese speakers. J Voice. 2024;1997(24):142-5. https://doi.org/10.1016/j.jvoice.2024.04.021 PMid:38724311.
    » https://doi.org/10.1016/j.jvoice.2024.04.021
  • 7Englert MT, Behlau M, Lucero JC. Validação do Acoustic Voice Quality Index (AVQI v. 03.01) e do Acoustic Breathiness Index (ABI) para o português brasileiro [tese]. São Paulo: Universidade Federal de São Paulo, Escola Paulista de Medicina; 2020.
  • 8Latoszek BBV, Maryn Y, Gerrits E, De Bodt M. A meta‑analysis: acoustic measurement of roughness and breathiness. J Speech Lang Hear Res. 2018;61(2):298-323. https://doi.org/10.1044/2017_JSLHR-S-16-0188 PMid:29392295.
    » https://doi.org/10.1044/2017_JSLHR-S-16-0188
  • 9Rutjes AWS, Reitsma JB, Di Nisio M, Smidt N, van Rijn JC, Bossuyt PMM. Evidence of bias and variation in diagnostic accuracy studies. CMAJ. 2006;174(4):469-76. https://doi.org/10.1503/cmaj.050090 PMid:16477057.
    » https://doi.org/10.1503/cmaj.050090
  • 10Roy N, Barkmeier-Kraemer J, Eadie T, Sivasankar MP, Mehta D, Paul D, et al. Evidence-based clinical voice assessment: a systematic review. Am J Speech Lang Pathol. 2013;22(2):212-26. https://doi.org/10.1044/1058-0360(2012/12-0014) PMid:23184134.
    » https://doi.org/10.1044/1058-0360(2012/12-0014)
  • 11Deliyski DD, Shaw HS, Evans MK. Adverse effects of environmental noise on acoustic voice quality measurements. J Voice. 2005;19(1):15-28. https://doi.org/10.1016/j.jvoice.2004.07.003 PMid:15766847.
    » https://doi.org/10.1016/j.jvoice.2004.07.003
  • 12Maryn Y, Roy N, De Bodt M, Van Cauwenberge P, Corthals P. Acoustic voice analysis: does vowel choice influence the diagnostic value? J Voice. 2019;33(5):666.e1-9.
  • 13Titze IR, Lemke J, Montequin D. Voicing and silence periods in continuous speech. J Acoust Soc Am. 2020;107(2):1065-76.
  • 14Bossuyt PM, Reitsma JB, Bruns DE, Gatsonis CA, Glasziou PP, Irwig L, et al, and the STARD Group. STARD 2015: an updated list of essential items for reporting diagnostic accuracy studies. Radiology. 2015;277(3):826-32. https://doi.org/10.1148/radiol.2015151516 PMid:26509226.
    » https://doi.org/10.1148/radiol.2015151516
  • 15Brasil. Instituto Brasileiro de Geografia e Estatística. Pesquisa Nacional por Amostra de Domicílios Contínua: resultados 2022. Rio de Janeiro: IBGE; 2022.
  • 16Behlau M, Zambon F, Guerrieri AC, Roy N. Epidemiology of voice disorders in teachers and nonteachers in Brazil: prevalence and adverse effects. J Voice. 2012;26(5):665.e9-18. https://doi.org/10.1016/j.jvoice.2011.09.010 PMid:22516316.
    » https://doi.org/10.1016/j.jvoice.2011.09.010
  • 17Yamasaki R, Madazio G, Leão SHS, Padovani M, Azevedo R, Behlau M. Auditory-perceptual evaluation of normal and dysphonic voices using the Voice Deviation Scale. J Voice. 2017;31(1):67-71. https://doi.org/10.1016/j.jvoice.2016.01.004 PMid:26873420.
    » https://doi.org/10.1016/j.jvoice.2016.01.004
  • 18Boersma P, Weenink D. Praat: doing phonetics by computer. Version 6.0.37 [software]. Amsterdam: University of Amsterdam; 2018.
  • 19Abreu SR, Moraes RM, Martins PN, Lopes LW. VoxMore: technological artifact to assist voice acoustic evaluation in the teaching-learning process and clinical practice. CoDAS. 2023;35(6):e20220166. https://doi.org/10.1590/2317-1782/20232022166pt PMid:37909540.
    » https://doi.org/10.1590/2317-1782/20232022166pt
  • 20Hosmer DW Jr, Lemeshow S. Applied logistic regression. 2nd ed. New York: Wiley; 2000. https://doi.org/10.1002/0471722146
    » https://doi.org/10.1002/0471722146
  • 21Abreu SR. Índice do grau geral do desvio vocal: desenvolvimento, avaliação e validação de um modelo de suporte à decisão para os falantes do português brasileiro [tese]. João Pessoa: Universidade Federal da Paraíba; 2024.
  • 22Zhao L, Xu R, Zhu H, Zhang L. Predictive values of acoustic voice parameters for diagnosing vocal fold pathologies. Clin Otolaryngol. 2018;43(3):745-51.
  • 23Maryn Y, Corthals P, Van Cauwenberge P, Roy N, De Bodt M. Toward improved ecological validity in the acoustic measurement of overall voice quality: combining continuous speech and sustained vowels. J Voice. 2009;24(5):540-55. https://doi.org/10.1016/j.jvoice.2008.12.014 PMid:19883993.
    » https://doi.org/10.1016/j.jvoice.2008.12.014
  • 24Latoszek BBV, Mayer J, Watts CR, Lehnert B. Advances in clinical voice quality analysis with VOXplot. J Clin Med. 2023;12(14):4644. https://doi.org/10.3390/jcm12144644 PMid:37510759.
    » https://doi.org/10.3390/jcm12144644
  • 25Nguyen DD, Novakovic D, Madill C. Voice disorder discrimination using vowel acoustic measures in female speakers. Int J Lang Commun Disord. 2024;59(5):2087-102. https://doi.org/10.1111/1460-6984.13081 PMid:38884559.
    » https://doi.org/10.1111/1460-6984.13081
  • 26Fawcett T. An introduction to ROC analysis. Pattern Recognit Lett. 2006;27(8):861-74. https://doi.org/10.1016/j.patrec.2005.10.010
    » https://doi.org/10.1016/j.patrec.2005.10.010
  • 27Leite DRA. Desenvolvimento de um modelo de classificação da tipologia dos sinais vocais com base no deep learning [tese]. João Pessoa: Universidade Federal da Paraíba; 2022.
  • 28Cappellari VM, Cielo CA. Características vocais acústicas de crianças pré-escolares. Rev Bras Otorrinolaringol. 2008;74(2):82-8. https://doi.org/10.1590/S0034-72992008000200018
    » https://doi.org/10.1590/S0034-72992008000200018
  • 29Parikh R, Mathai A, Parikh S, Chandra Sekhar G, Thomas R. Understanding and using sensitivity, specificity and predictive values. Indian J Ophthalmol. 2008;56(1):45-50. https://doi.org/10.4103/0301-4738.37595 PMid:18158403.
    » https://doi.org/10.4103/0301-4738.37595
  • 30Patel RR, Awan SN, Barkmeier-Kraemer J, Courey M, Deliyski D, Eadie T, 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;27(3):887-905. https://doi.org/10.1044/2018_AJSLP-17-0009 PMid:29955816.
    » https://doi.org/10.1044/2018_AJSLP-17-0009

Submetido em:
04/08/2025

Aceito em:
15/12/2025

6a807967a9539575ee6c9294 codas Articles

CoDAS

Share this page
Page Sections