Archivo Abierto Institucional de la Universidad Carlos III de Madrid >
Departamento de Teoría de la Señal y Comunicaciones >
Grupo de Procesado Multimedia >
DTSC - GPM - Artículos de Revistas >
Please use this identifier to cite or link to this item:
|Title: ||Characterization of Healthy and Pathological Voice Through Measures Based on Nonlinear Dynamics|
|Author(s): ||Henríquez, Patricia|
Alonso, Jesús B.
Ferrer, Miguel A.
Travieso, Carlos M.
Godino-Llorente, Juan I.
|Issued date: ||Aug-2009|
|Citation: ||Patricia Henríquez, Jesús B. Alonso, Miguel A. Ferrer, Carlos M. Travieso, Juan I. Godino-Llorente, and Fernando Díaz-de-María, “Characterization of Healthy and Pathological Voice Through Measures Based on Nonlinear Dynamics” IEEE Transactions on Audio, Speech and Language Processing, Vol. 17, Nº 6, pp. 1186-1195, Aug. 2009.|
|Abstract: ||In this paper, we propose to quantify the quality of the recorded voice through objective nonlinear measures. Quantification of speech signal quality has been traditionally carried out with linear techniques since the classical model of voice production is a linear approximation. Nevertheless, nonlinear behaviors in the voice production process have been shown. This paper studies the usefulness of six nonlinear chaotic measures based on nonlinear dynamics theory in the discrimination between two levels of voice quality: healthy and pathological. The studied measures are first- and second-order Renyi entropies, the correlation entropy and the correlation dimension. These measures were obtained from the speech signal in the phase-space domain. The values of the first minimum of mutual information function and Shannon entropy were also studied. Two databases were used to assess the usefulness of the measures: a multiquality database composed of four levels of voice quality (healthy voice and three levels of pathological voice); and a commercial database (MEEI Voice Disorders) composed of two levels of voice quality (healthy and pathological voices). A classifier based on standard neural networks was implemented in order to evaluate the measures proposed. Global success rates of 82.47% (multiquality database) and 99.69% (commercial database) were obtained.|
|Publisher version: ||http://dx.doi.org/10.1109/TASL.2009.2016734|
Characterization of Healthy and Pathological Voice
|Appears in Collections:||DTSC - GPM - Artículos de Revistas|
Items in E-Archivo are protected by copyright, with all rights reserved, unless otherwise indicated.