Characterization Methods for the Detection of Multiple Voice Disorders: Neurological, Functional, and Laryngeal Diseases

Abstract

This paper evaluates the accuracy of different characterization methods for the automatic detection of multiple speech disorders. The speech impairments considered include dysphonia in people with Parkinson's disease (PD), dysphonia diagnosed in patients with different laryngeal pathologies (LP), and hypernasality in children with cleft lip and palate (CLP). Four different methods are applied to analyze the voice signals including noise content measures, spectral-cepstral modeling, nonlinear features, and measurements to quantify the stability of the fundamental frequency. These measures are tested in six databases: three with recordings of PD patients, two with patients with LP, and one with children with CLP. The abnormal vibration of the vocal folds observed in PD patients and in people with LP is modeled using the stability measures with accuracies ranging from 81% to 99% depending on the pathology. The spectral-cepstral features are used in this paper to model the voice spectrum with special emphasis around the first two formants. These measures exhibit accuracies ranging from 95% to 99% in the automatic detection of hypernasal voices, which confirms the presence of changes in the speech spectrum due to hypernasality. Noise measures suitably discriminate between dysphonic and healthy voices in both databases with speakers suffering from LP. The results obtained in this study suggest that it is not suitable to use every kind of features to model all of the voice pathologies; conversely, it is necessary to study the physiology of each impairment to choose the most appropriate set of features.

The Use of LPC and Wavelet Transform for Influenza Disease Modeling

“…The FAR, FRR, S, P, PP, AC, and EF scores were calculated (see Table 2), and we can see that the proposed method achieved very high scores, particularly for Normal with Influenza. The value based on the recognition rate of the proposed systems was also compared with other published recognition systems, such as power spectrum density (PSD) [12], LPC [13], and MFCC [12]. Table 3 tabulates the comparative results obtained on the recorded database.…”

“…These factors affect their functionality with different levels of effects, and somehow change the sound these organs produce. Every pathological (disease) factor may have specific changes in the human sound, modeling these changes will enable us to detect some diseases by the sound of the patient [11][12][13][14].…”

Improving Quality of Life: Home Care for Chronically Ill and Elderly People

“…The interest in emotion recognition from speech has increased in the last decade because emotion recognition can improve the quality of services and the quality of life of people. It is possible to make predictions by using a supervised learning scheme, whose final scope is determining the health status of individuals [29]. Through a set of features, it is possible to identify and characterize states of people that can be as common as unpredictable such as emotional states.…”

Monitoring Parkinson Disease from speech articulation kinematics

“…PD-induced neuromotor degeneration speech monitoring has been classicaly based on phonation (fundamental frequency, energy, jitter, shimmer, noise-harmonic ratio, biomechanical parameters (Gómez et al, 2017a;Mekyska et al, 2015;Orozco et al, 2015). Speech articulation is also a possible target to explore.…”