Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{201447,
        author = {Vanitha S L and Nikhil N and Sinchana R and Girija Suchitra M},
        title = {AUTOMATED NASALANCE ANALYSIS USING MACHINE LEARNING FOR SPEECH DISORDER DIAGNOSIS},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {4376-4384},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=201447},
        abstract = {Nasalance measurement is a fundamental component of speech evaluation, particularly for identifying resonance-related conditions including hypernasality and hyponasality, both of which are widely encountered in patients with cleft palate, neurological conditions, and structural speech impairments. Traditional clinical assessment approaches largely depend on manual expert evaluation and perceptual interpretation, which can introduce variability, inconsistency, and delays in arriving at diagnostic conclusions. To overcome these shortcomings, this study introduces the NasalanceAI Clinical Analyzer, an AI-powered framework that performs automated nasalance evaluation using machine learning. The system takes clinical and demographic inputs—mean nasalance score, age, gender, and language—and computes a Z-score representing the degree of deviation from typical resonance norms. Speech is then classified as hyponasal, normal, or hypernasal, and further graded by severity as mild, moderate, or severe. The system additionally incorporates automated report generation and patient data management features to streamline clinical operations. Experimental results show that the Logistic Regression classifier achieved an accuracy of 80.5%, providing a strong balance among predictive capability, model transparency, and generalizability for medical applications. By facilitating objective, repeatable, and efficient evaluation, the system lessens reliance on manual processes and strengthens the dependability of speech disorder diagnosis. The system overall highlights the capacity of AI to enable scalable and accessible clinical speech evaluation tools.},
        keywords = {Nasalance, Speech Analysis, Machine Learning, Clinical AI, Regression Model, Healthcare Automation},
        month = {May},
        }