Related Experiment Video
Updated: Apr 5, 2026

A Protocol for Comprehensive Assessment of Bulbar Dysfunction in Amyotrophic Lateral Sclerosis ALS
Published on: February 21, 2011
Characterization Methods for the Detection of Multiple Voice Disorders: Neurological, Functional, and Laryngeal
This study shows that specific voice analysis methods accurately detect speech disorders like Parkinson
Area of Science:
- Speech pathology
- Biomedical engineering
- Acoustic analysis
Background:
- Automatic detection of speech disorders is crucial for timely diagnosis and treatment.
- Different speech impairments, including Parkinson's disease (PD) related dysphonia, laryngeal pathologies (LP) dysphonia, and cleft lip and palate (CLP) related hypernasality, present unique acoustic characteristics.
- Selecting appropriate voice analysis features is key to accurately characterizing these diverse pathologies.
Purpose of the Study:
- To evaluate the accuracy of various characterization methods for automatically detecting multiple speech disorders.
- To determine the most effective voice analysis features for specific pathologies: Parkinson's disease dysphonia, laryngeal pathologies dysphonia, and hypernasality in children with cleft lip and palate.
- To highlight the importance of matching analysis techniques to the underlying physiology of each speech impairment.
Main Methods:
- Analysis of voice signals using four distinct methods: noise content measures, spectral-cepstral modeling, nonlinear features, and fundamental frequency stability measurements.
- Testing these methods across six databases comprising recordings from patients with PD, LP, and children with CLP.
- Utilizing stability measures for vocal fold vibration pathologies (PD, LP) and spectral-cepstral features for hypernasality.
Main Results:
- Stability measures achieved high accuracies (81%–99%) in detecting dysphonia associated with Parkinson's disease and laryngeal pathologies.
- Spectral-cepstral features demonstrated excellent accuracy (95%–99%) in the automatic detection of hypernasality in children with cleft lip and palate.
- Noise measures effectively differentiated between dysphonic and healthy voices in patients with laryngeal pathologies.
Conclusions:
- The study underscores that a one-size-fits-all approach is inadequate for modeling all voice pathologies.
- Tailoring the selection of voice analysis features to the specific physiological characteristics of each speech disorder is essential for accurate detection.
- This research provides valuable insights for developing more precise diagnostic tools for a range of speech impairments.
More Related Videos
06:22Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
Published on: September 19, 2025
07:45Minimally Invasive Murine Laryngoscopy for Close-Up Imaging of Laryngeal Motion During Breathing and Swallowing
Published on: December 1, 2023
Related Concept Videos
Larynx
Anatomy of the Larynx
The larynx consists of various components, including cartilage, muscles, and vocal cords. Its structure includes three large unpaired cartilages—the thyroid, cricoid, and epiglottis—and three smaller paired cartilages—the arytenoids,...
Physical Assessment of the Respiratory Tract IV: Auscultation
Breath Sounds
Breath sounds are categorized into vesicular, bronchovesicular, and bronchial.
Respiratory System Abnormal Finding II: Palpation and Auscultation
Palpation Findings
During a respiratory assessment, palpation can reveal several vital abnormalities:
Assessment of Airway, Skin Color, and Use of Accessory Muscles
Introduction
The initial evaluation of a patient's respiratory system...
Myasthenia Gravis: Diagnostic Tests
The edrophonium test is a diagnostic tool for myasthenia gravis. It involves...