Speech-Based Parameter Estimation of an Asymmetric Vocal Fold Oscillation Model and Its Application in Discriminating Vocal Fold Pathologies

TL;DR

This paper introduces a speech-based method to estimate parameters of an asymmetric vocal fold model, enabling discrimination of vocal pathologies without invasive measurements, thus offering a scalable clinical tool.

Contribution

It presents a novel approach to estimate vocal fold model parameters directly from speech signals, especially addressing asymmetry and pathology differentiation.

Findings

Parameters estimated from speech can distinguish different vocal fold pathologies.

Asymmetric model parameters effectively reflect vocal fold deviations.

Speech-based parameter estimation offers a non-invasive alternative to traditional methods.

Abstract

So far, several physical models have been proposed for the study of vocal fold oscillations during phonation. The parameters of these models, such as vocal fold elasticity, resistance, etc. are traditionally determined through the observation and measurement of the vocal fold vibrations in the larynx. Since such direct measurements tend to be the most accurate, the traditional practice has been to set the parameter values of these models based on measurements that are averaged across an ensemble of human subjects. However, the direct measurement process is hard to revise outside of clinical settings. In many cases, especially in pathological ones, the properties of the vocal folds often deviate from their generic values---sometimes asymmetrically wherein the characteristics of the two vocal folds differ for the same individual. In such cases, it is desirable to find a more scalable way to adjust the model parameters on a case by case basis. In this paper, we present a novel and alternate way to determine vocal fold model parameters from the speech signal. We focus on an asymmetric model and show that for such models, differences in estimated parameters can be successfully used to discriminate between voices that are characteristic of different underlying vocal fold pathologies.