Modern possibilities for the diagnosis of voice disorders using computer acoustic analysis of voice and artificial intelligence
- 4 September 2026
- journal article
- Published by Media Sphere Publishing Group in Russian Bulletin of Otorhinolaryngology
- Vol. 91 (4)
Abstract
Objective. The purpose of the review is to analyze modern approaches to the diagnosis of voice disorders using AI and acoustic analysis, as well as to evaluate their effectiveness and prospects for implementation in clinical practice. Research design. A review of domestic and foreign literature sources on the use of computer acoustic analysis and AI technologies in the diagnosis of diseases of the vocal apparatus is carried out. Material and methods. The material for the analysis was publications in scientific journals, the results of clinical trials, data on the use of specialized software systems (PRAAT, MDVP, LingWaves) and machine learning-based systems (SVM, CNN, RNN and their combinations). Data on diagnostic accuracy, interpretability of results, and applicability in real clinical practice were considered. Results. Acoustic analysis of the voice makes it possible to detect pathological changes in the early stages, before the appearance of pronounced symptoms. The PRAAT and MDVP programs have become the standard in assessing the spectral and temporal characteristics of a voice. The introduction of AI has significantly improved diagnostic accuracy (up to 95–97% in individual studies). Machine learning algorithms and deep neural networks automate diagnostics, allow you to identify hidden patterns and use data obtained even from mobile devices. However, there are still unresolved issues of database standardization, interpretability of models, and ethical and legal aspects of their implementation. Despite the high efficiency of technologies, their use requires the development of uniform standards, ensuring the transparency of algorithms and multidisciplinary interaction of specialists.Keywords
This publication has 39 references indexed in Scilit:
- Computer Vision and Videomics in Otolaryngology–Head and Neck SurgeryOtolaryngologic Clinics of North America, 2024
- A Scoping Review of Artificial Intelligence Detection of Voice Pathology: Challenges and OpportunitiesOtolaryngology–Head and Neck Surgery, 2024
- Generative artificial intelligence in otolaryngology–head and neck surgery editorial: be an actor of the future or followerEuropean Archives of Oto-Rhino-Laryngology, 2024
- Automated voice pathology discrimination from audio recordings benefits from phonetic analysis of continuous speechBiomedical Signal Processing and Control, 2023
- Artificial Intelligence in Head and Neck Cancer: A Systematic Review of Systematic ReviewsAdvances in Therapy, 2023
- Developing an Artificial Intelligence Tool to Predict Vocal Cord Pathology in Primary Care SettingsThe Laryngoscope, 2022
- Diagnosis of Early Glottic Cancer Using Laryngeal Image and Voice Based on Ensemble Learning of Convolutional Neural Network ClassifiersJournal of Voice, 2022
- A New iPhone Application for Voice Quality Assessment Based on the GRBAS ScaleThe Laryngoscope, 2020
- A Survey on Machine Learning Approaches for Automatic Detection of Voice DisordersJournal of Voice, 2019
- Analysis and Classification of Voice Pathologies Using Glottal Signal ParametersJournal of Voice, 2016