ZYLO:THE SMART READING ASSISTANT SYSTEM FOR DYSLEXIA

 The integration of adaptive AI technologies with accessible design provides a personalized and effective reading solution for dyslexic readers. By integrating real-time text adaptation, text-to-speech with highlighting, and speech recognition feedback, the proposed system overcomes major limitations in state-of-the-art reading applications. Personalized support, multisensory engagement, and tracking of progress will be ensured without sacrificing usability across a variety of learning contexts. Overall, natural language processing with machine learning and user-centered design come together to provide a comprehensive and smart reading assistant that considerably improves reading proficiency in neurodiverse learners.

[1]     H.-W. Bae, H.-S. Oh, S.-B. Kim, and S.-W. Lee, “UnitCorrect: UnitBased Mispronunciation Correcting System With a DTW-Based Detection,” IEEE Transactions on Audio, Speech, and Language Processing,  vol.    33,              pp. 1753–1762, Apr.            2025,   doi: 10.1109/TASLPRO.2025.3559344. [2]     M. Rauschenberger, R. Baeza-Yates, and L. Rello, “Screening Dyslexia Using Visual Auditory Computer Games and Machine Learning,” 10.1109/ACCESS.2020.3048250. [3]     L. Song and R. Mao, “Effect of Text-to-Speech Tools on the Reading Comprehension of Students with Dyslexia,” International Journal of Emerging Technologies in Learning (iJET), vol. 17, no. 6, pp. 45–57, 2022, doi: 10.3991/ijet.v17i06.29753. [4]     R. Vinotha, D. Hepsiba, L. D. Vijay Anand, J. Andrew, and R. Jennifer Eunice, “Enhancing Dysarthric Speech Recognition through SepFormer and Hierarchical Attention Network Models with Multistage Transfer Learning,” Scientific Reports, 2024, doi: 10.1038/s41598-024-80764-w. [5]     L. Song and R. Mao, “Effect of Text-to-Speech Tools on the Reading Comprehension of Students with Dyslexia,” Journal of Arts, Society, and Education Studies, vol. 6, no. 2, p. 184, 2024, doi:10.69610/j.ases.20240723. [6]     D. V. Katsarou, E. Mantsos, S. Papadopoulou, M. Sofologi, E. Efthymiou, I. Vasileiou, K. Megari, M. Theodoratou, and G. A. Kougioumtzis, “Exploring AI Technology in Grammar Performance Testing for Children with Learning Disabilities,” Education Sciences, vol. 15, no. 3, article 351, 2025, doi: 10.3390/educsci15030351. [7]     S. R. Shahamiri, V. Lal, and D. Shah, “Dysarthric Speech Transformer: A Sequence-to-Sequence Dysarthric Speech Recognition System,” IEEE Transactions on Neural Networks and Learning Systems, vol. XX, no. YY, pp. ZZ–AA, 2025, doi:10.1109/TNSRE.2023.3307020. [8]     G. Almgren Bäck, E. Lindeblad, C. Elmqvist, and I. Svensson, “Dyslexic Students’ Experiences in Using Assistive Technology to Support Written Language Skills: A Five-Year Follow-Up,” Disability and Rehabilitation: Assistive Technology, vol. 19, no. 4, 2024, pp. 1217– 1227, doi: 10.1080/17483107.2022.2161647. [9]     M. G. Gonzales, P. Corcoran, N. Harte, and M. Schukat, “Joint Speech- Text Embeddings for Multitask Speech Processing,” IEEE  10.1109/ACCESS.2024.3473743. [10]   K. Azizah, “Zero-Shot Voice Cloning Text-to-Speech for Dysphonia Disorder Speakers,” IEEE Access, vol. 12, 2024, pp. 63528–63547, doi:10.1109/ACCESS.2024.3396377.