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{201862,
        author = {Saylee Honmode and Saniya Kabadi and Priyanshu Jadhav and Shweta Phadnis},
        title = {Cleft Speech AI: Smart Speech Therapy for Post-Surgical Cleft Palate},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {8101-8105},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=201862},
        abstract = {Cleft palate is a congenital condition that significantly affects speech clarity, even after surgical correction. Continuous speech therapy is essential for recovery; however, access to speech-language pathologists is often limited by geographical and financial constraints. This study proposes Cleft Speech AI, a web-based platform that leverages deep learning techniques to assist with speech evaluation and therapy. The system records a child’s speech, processes it using Mel frequency central coefficients, and analyzes it using a hybrid CNN-LSTM model. The model provides real-time feedback to improve speech quality. The experimental results demonstrated an accuracy of approximately 90},
        keywords = {Cleft Palate, Speech Therapy, Artificial Intelligence, Deep Learning, CNN-LSTM, Web Application},
        month = {May},
        }