Skip to main content
Springer Nature Link
Log in

Nonlinear Dynamics for Hypernasality Detection in Spanish Vowels and Words

  • Published:
Cognitive Computation Aims and scope Submit manuscript

Abstract

A novel technique for characterizing hypernasal vowels and words using nonlinear dynamics is presented considering different complexity measures that are mainly based on the analysis of the time-delay embedded space. After the characterization stage, feature selection is performed by means of two different strategies: principal components analysis and sequential floating feature selection. The final decision about the presence or absence of hypernasality is carried out using a Soft Margin-Support Vector Machine. The database used in the study is composed of the five Spanish vowels uttered by 266 children, 110 healthy and 156 labeled as hypernasal by a experienced voice therapist. The database also includes the words /coco/ and /gato/ uttered by 119 children; 65 of which were diagnosed as hypernasal and the rest 54 as healthy. The results are presented in terms of accuracy, sensitivity and specificity. ROC curves are also included as a widely accepted way to measure the performance of a detection system. The experiments show that the proposed methodology achieves an accuracy of up to 92.08 % using, together, the best subset of features extracted from every vowel and 89.09 % using the combination of the most relevant features in the case of words.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Henningsson GE, Isberg AM. Velopharyngeal movement patterns in patients alternating between oral and glottal articulation: a clinical and cineradiographical study citation. Cleft Palate J. 1986;23(1):1–9.

    PubMed  CAS  Google Scholar 

  2. Kummer AW. Cleft palate and craniofacial anomalies: effects on speech and resonance. 2nd ed. Stamford: Cengage Learning; 2007.

    Google Scholar 

  3. Murillo-Rendón S, Orozco-Arroyave JR, Vargas-Bonilla JF, Arias-Londoño JD, Castellanos-Domínguez CG. “Automatic detection of hypernasality in children”, new challenges on bioinspired applications, vol 6687. Berlin: Springer; 2011. p. 167–174.

  4. Maier A, Hönig F, Hacker C, Shuster M, Nöth E. Automatic evaluation of characteristic speech disorders in children with cleft lip and palate. In: 11th international conference on spoken language processing, Brisbane-Australia; 2008. p. 1757–1760.

  5. Golding KK. therapy techniques for cleft palate speech and related disorders. San Diego: Singular Thomson Learning [Ed]; 2001.

    Google Scholar 

  6. Giovanni A, Ouaknine M, Guelfucci R, Yu T, Zanaret M, Triglia JM. Nonlinear behavior of vocal fold vibration: the role of coupling between the vocal folds. J Voice. 1999;13(4):456–476.

    Google Scholar 

  7. Orozco-Arroyave JR, Murillo-Rendón S, Álvarez-Meza A, Arias-Londoño JD, Delgado-Trejos E, Vargas-Bonilla JF, Castellanos-Domínguez CG. Automatic selection of acoustic and non-linear dynamic features in voice signals for hypernasality detection. In: Proceedings of Interspeech. 2011. p. 529–532.

  8. Henriquez P, Alonso JB, Ferrer MA, Travieso CM, Godino-Llorente JI, Díaz-de-María F. Characterization of healthy and pathological voice through measures based on nonlinear dynamics. IEEE Trans Audio Speech Lang Process. 2009;17(6):1186–1195.

    Article  Google Scholar 

  9. Delgado-Trejos E, Sepúlveda FA, Röthlisberger S, Castellanos-Domínguez G. The Rademacher complexity model over acoustic features for improving robustness in hypernasal speech detection. In: Computers and simulation in modern science, vol V. UK: WSEAS Press, University of Cambridge; 2011. p.130–135.

  10. Arias-Londoño JD, Godino-Llorente JI, Sáenz-Lechón N, Osma-Ruíz V, Castellanos-Domínguez G. Automatic detection of pathological voices using complexity measures, noise parameters and mel-cepstral coefficients. IEEE Trans Biomed Eng. 2011;58(2):370–379.

    Article  PubMed  Google Scholar 

  11. Lewis KE, Watterson T, Quint T. The effect of vowels on nasalance scores. Cleft Palate Craniofac J. 2000;37(6):584–589.

    Article  CAS  Google Scholar 

  12. Kuehn DP, Moller KT. Speech and language issues in the cleft palate population: the state of the art. Cleft Palate Craniofac J. 2000;37(4):1–35.

    Google Scholar 

  13. Titze IR. Workshop on acoustic voice analysis: summary statement. National Center for Voice and Speech, Denver, 1994.

  14. Jiang J, Zhang Y, McGilligan C. Chaos in voice, from modeling to measurement. J Voice. 2006;20(1):2–17.

    Article  PubMed  Google Scholar 

  15. Takens F. Detecting strange attractors in turbulence. Dynamical systems and turbulence: lecture notes in mathematics, vol 898. Springer: Berlin; 1981. p. 366–381.

  16. Kennel MB, Brown R, Abarbanel HDI. Determining embedding dimension for phase-space reconstruction using geometrical construction. Phys Rev A. 1992;45(6):3403-3411.

    Article  PubMed  Google Scholar 

  17. Fraser AM, Swinney HL. Independent coordinates for strange attractors from mutual information. Phys Rev A. 1986;33(2):1134–1140.

    Article  PubMed  Google Scholar 

  18. Shaheen A, Roy N, Jiang JJ. Nonlinear dynamic analysis of disordered voice: the relationship between the correlation dimension (D2) and pre-/post-treatment change in perceived dysphonia severity. J Voice. 2010;24(3):285–293.

    Article  Google Scholar 

  19. Grassberger P, Procaccia I. Measuring the strangeness of strange attractors. Physica D. 1983;9:189–208.

    Article  Google Scholar 

  20. Abarbanel HDI. Analysis of observed chaotic data, 1st ed. Inst. for Nonlinear Science. Springer: New York; 1996.

  21. Rosenstein MT, Collins JJ, De Luca CJ. A practical method for calculating largest Lyapunov exponents from small data sets. Physica D. 1993;65:117–134.

    Article  Google Scholar 

  22. Oseledec VA. A multiplicative ergodic theorem. Lyapunov characteristic numbers for dynamical systems. Trans Moscow Math Soc. 1968;19:197–231.

    Google Scholar 

  23. Hurst HE, Black RP, Simaika YM. Long-term storage: an experimental study. 1st ed. London: Constable; 1965.

    Google Scholar 

  24. Kaspar F, Shuster HG. Easily calculable measure for complexity of spatiotemporal patterns. Phys Rev A. 1987;36(2):842–848.

    Article  PubMed  Google Scholar 

  25. Jolliffe IT. Principal Component Analysis, 2nd Ed. Springer series in statistics. Springer: New York; 2002.

  26. Daza-Santacoloma G, Arias-Londoño JD, Godino-Llorente JI, Sáenz-Lechón N, Osma-Ruíz V, Castellanos-Domínguez G. Dynamic feature extraction: an application to voice pathology detection. Intell Autom Soft Comput 2009;15(4):667–682.

    Google Scholar 

  27. Pudil P, Novovicova J, Kittler J. Floating search methods in feature selection. Patt Recogn Lett 1994;15(11):1119–1125.

    Article  Google Scholar 

  28. Scholköpf B, Smola AJ. Learning with Kernels. The MIT Press: Cambridge; 2002.

    Google Scholar 

  29. Lee GS, Wang CP, Fu S. Evaluation of hypernasality in vowels using voice low tone to high tone ratio. Cleft Palate J 2009;23(1):47–52.

    Article  CAS  Google Scholar 

Download references

Acknowledgments

This work was funded by ARTICA, financed by COLCIENCIAS and Ministerio de TIC in Colombia, project \(\hbox{N}^{\deg}\)1115-470-22055, in association with the Clínica Noel, Medellín. Also by CODI at Universidad de Antioquia, project MC11-1-03, by “Convocatoria 528 para estudios de doctorado en Colombia, generación del bicentenario, (COLCIENCIAS 2011)” and the project 2010238-PI/UAN-2011-473bit from Universidad Antonio Nariño, Colombia.

Author information

Authors and Affiliations

  1. DIEyT, Universidad de Antioquia, Medellín, Colombia

    J. R. Orozco-Arroyave & J. F. Vargas-Bonilla

  2. FIEyB, Universidad Antonio Nariño, Bogotá, Colombia

    J. D. Arias-Londoño

  3. DIEEyC, Universidad Nacional de Colombia, Manizales, Colombia

    S. Murillo-Rendón & G. Castellanos-Domínguez

  4. Grupo de LPH, Fundación Clínica Noel, Medellín, Colombia

    J. F. Garcés

Authors
  1. J. R. Orozco-Arroyave
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. J. F. Vargas-Bonilla
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. J. D. Arias-Londoño
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. S. Murillo-Rendón
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. G. Castellanos-Domínguez
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. J. F. Garcés
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to J. R. Orozco-Arroyave.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Orozco-Arroyave, J.R., Vargas-Bonilla, J.F., Arias-Londoño, J.D. et al. Nonlinear Dynamics for Hypernasality Detection in Spanish Vowels and Words. Cogn Comput 5, 448–457 (2013). https://doi.org/10.1007/s12559-012-9166-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12559-012-9166-z

Keywords