Characterization of Healthy and Pathological Voice Through Measures Based on Nonlinear Dynamics

TLDR

Quantification of speech signal quality has traditionally relied on linear techniques, yet nonlinear behaviors in voice production have been demonstrated. The study aims to quantify voice quality by applying six nonlinear chaotic measures to distinguish healthy from pathological voices. The authors extracted Renyi entropies, correlation entropy and dimension, mutual‑information minima, and Shannon entropy from phase‑space representations of speech signals, evaluated them on two databases, and classified the results with a standard neural network. The approach achieved global success rates of 82.47 % on the multi‑quality database and 99.69 % on the commercial MEEI Voice Disorders database.

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.