Research on Biomedical Engineering
Research on Biomedical Engineering
Original article

KSG estimation of reconstruction delay to detect vocal disorders in nonlinear dynamical analysis - Published Ahead of Print

Mikaelle Oliveira Santos, Juliana Martins de Assis, Vinícius Jefferson Dias Vieira, Francisco Marcos de Assis


Introduction: This research investigates the applicability of a relatively new estimator of mutual information, KSG estimator, to find the reconstruction delay of phase space in dynamical systems. There are evidences that the KSG estimator is more accurate than the naive method commonly used. Methods: In this paper we estimated mutual information between the voice signals and their delayed versions, with KSG method. The voice signals were obtained from a disordered voice database. Then, we found the reconstruction delay where mutual information reached its first minimum. We applied the encountered value of reconstruction delay in linear discriminant analysis, in order to discriminate between healthy and pathological voices or to discriminate between pathologies. Discrimination between voice pathologies using nonlinear measurements is still not much explored. Moreover, in this paper we used a single nonlinear measurement: reconstruction delay. Results: The results show that the reconstruction delay obtained with KSG method has increased classification rates in most cases, in terms of accuracy, sensitivity and specificity, when compared to the naive estimator usually adopted. Conclusion: The KSG estimator is a promising technique to improve the diagnosis of voice related pathologies.


KSG estimator, Reconstruction delay, Vocal disorders.


Abarbanel HD. Analysis of observed chaotic data. USA: Springer; 1996.

Assis JM, Santos MO, Assis FM. Auditory stimuli coding by postsynaptic potential and local field potential features. PLoS One. 2016; 11(8):e0160089. PMid:27513950.

Awan SN, Roy N, Jiang JJ. Nonlinear dynamic analysis of disordered voice: the relationship between the correlation dimension (D 2) and Pre-/Post-treatment change in perceived dysphonia severity. J Voice. 2010; 24(3):285-93. PMid:19502002.

Barbosa-Branco A, Romariz MS. Doenças das cordas vocais e sua relação com o trabalho. Comum Ciênc Saúde. 2006; 17(1):37-45.

Chai L, Sprecher AJ, Zhang Y, Liang Y, Chen H, Jiang JJ. Perturbation and nonlinear dynamic analysis of adult male smokers. J Voice. 2011; 25(3):342-7. PMid:20472394.

Costa WCA, Assis FM, Aguiar BG No, Costa SLC, Vieira VJD. Pathological voice assessment by recurrence quantification analysis. In: Proceedings of the 2012 ISSNIP Biosignals and Biorobotics Conference: Biosignals and Robotics for Better and Safer Living (BRC); 2012 Jan 9-11; Manaus, Brazil. USA: IEEE; 2012. p. 1-6.

Costa WCA, Costa SLNC, Assis FM, Aguiar BG No. Classificação de sinais de vozes saudáveis e patológicas por meio da combinação entre medidas da análise dinâmica não linear e codificação preditiva linear. Res Biomed Eng. 2013; 29(1):3-14.

Cover TM, Thomas JA. Elements of information theory. 2nd ed. USA: John Wiley & Sons; 2006.

Cummings L. Clinical linguistics. Edimburgo: Edinburgh University Press; 2008.

Darbellay GA, Vajda I. Estimation of the information by na adaptive partitioning of the observation space. IEEE Trans Inf Theory. 1999; 45(4):1315-21.

Davis SB. Acoustic characteristics of normal and pathological voices. Speech and Language. 1979; 1:271-335.

Fraser AM, Swinney HL. Independent coordinates for strange attractors from mutual information. Phys Rev A Gen Phys. 1986; 33(2):1134-40. PMid:9896728.

Henriquez P, Alonso JÚB, Ferrer MA, Travieso CM, Godino-Llorente JI, Diaz-de-Maria F. Characterization of healthy and pathological voice through measures based on nonlinear dynamics. IEEE Trans Audio Speech Lang Process. 2009; 17(6):1186-95.

Jiang JJ, Zhang Y, McGilligan C. Chaos in voice, from modeling to measurement. J Voice. 2006; 20(1):2-17. PMid:15964740.

Kantz H, Schreiber T. Nonlinear time series analysis. Cambridge: Cambridge University Press; 2004.

Kay Elemetrics Corp. Disordered voice database. USA: Kay Elemetrics Corp.; 1994.

Kokkinos I, Maragos P. Nonlinear speech analysis using models for chaotic systems. IEEE Trans Speech Audio Process. 2005; 13(6):1098-109.

Kozachenko L, Leonenko NN. Sample estimate of the entropy of a random vector. Probl. Peredachi Inf. 1987; 23(2):9-16.

Kraskov A, Stögbauer H, Grassberger P. Estimating mutual information. Phys Rev E Stat Nonlin Soft Matter Phys. 2004; 69(6):066138. PMid:15244698.

Pinho PHU, Couras MFKB, Dantas ECS, Costa SLC, Correia SEN. Classificação de patologias laríngeas por meio de características do espaço de fase reconstruído. In: SBrT2016: Anais do 34° Simpósio Brasileiro de Telecomunicações; 2016 ago 30 set 2; Santarém, PA. Rio de Janeiro: SBrT; 2016. p. 583-7.

Pontes P, Brasolotto A, Behlau M. Glottic characteristics and voice complaint in the elderly. J Voice. 2005; 19(1):84-94. PMid:15766853.

Quek F, Harper M, Haciahmetoglou Y, Chen L, Ramig LO. Speech pauses and gestural holds in parkinsons disease. In: ICSLP2002 - INTERSPEECH 2002: Proceedings of the 7th International Conference on Spoken Language Processing; 2002 Sep 16-20; Denver, Colorado, USA. Denver: Causal Productions Pty; 2002. p. 2485-2488.

Rabiner LR, Schafer RW. Digital processing of speech signals. USA: Prentice Hall; 1978.

Reynolds DA, Heck LP. Automatic speaker recognition. In: Proceedings of the AAAS 2000 Meeting Humans, Computers and Speech Symposium; 2000; Washington. Washington, DC: American Association for the Advancement of Science; 2000. p. 101-104.

Shannon CE, Weaver W. The mathematical theory of information. Urbana: Illinois Books Edition; 1949.

Vaziri G, Almasganj F, Behroozmand R. Pathological assessment of patients’ speech signals using nonlinear dynamical analysis. Comput Biol Med. 2010; 40(1):54-63. PMid:19962694.

5ba6e19f0e88255f6136c1ed rbejournal Articles
Links & Downloads

Res. Biomed. Eng.

Share this page
Page Sections