| Issue |
ITM Web Conf.
Volume 81, 2026
International Conference on Emerging Technologies for Multidisciplinary Innovation and Sustainability (ETMIS 2025)
|
|
|---|---|---|
| Article Number | 01008 | |
| Number of page(s) | 15 | |
| DOI | https://doi.org/10.1051/itmconf/20268101008 | |
| Published online | 23 January 2026 | |
Handwritten input to speech conversion using transfer learning
Computer Science and Systems Engineering, Lendi Institute of Engineering and Technology, Vizianagaram, India
* Corresponding author: This email address is being protected from spambots. You need JavaScript enabled to view it.
System developed to transform handwritten text into clear, natural sounding speech attained by using a structured multi-step process. The steps include image preprocessing,clean and enhanced output,elimination of noise and improvement of readability.The unrefined input text is refined using Natural Language Processing(NLP).This refined text is transformed into human-like speech using advanced conversion methods.The system ensures improved recognition,accuracy,effective noise reduction and contextual correction providing smooth and natural speech output.The system is highly useful for education,healthcare,assistance and particularly for aiding visually challenged individuals.The combination of computer vision,deep learning,and language preprocessing bridges the gap between handwritten information and digital accessibility.
Key words: Handwritten Text / Recognition / Transfer Learning / Assistive Technology / Text-to-Speech / Inclusive Education / Tacotron2 / Wave Glow
© The Authors, published by EDP Sciences, 2026
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.

