IIIT-Hyderabad initiative expands learning access for visually impaired learners

IIIT-Hyderabad researchers have launched Drishti Library, an AI-powered initiative under the Bhashini mission to convert higher-education textbooks into Braille and audiobooks, improving access for visually impaired students across Indian languages

Hyderabad: For years, visually impaired students struggled with limited access to study material in higher education. The International Institute of Information Technology (IIIT) – Hyderabad researchers now seek to change that via their new digital initiative – Drishti Library, offering a more inclusive learning experience,

The initiative focuses on making higher education textbooks available in Braille and audiobook formats, starting with Punjabi and expanding across languages and disciplines. The library was unveiled at a recent symposium on Language AI – for accessibility.

---

Developed at IIIT-H by researcher Krishna Tulsiyan under the guidance of Prof CV Jawahar and Prof Gurpreet Singh Lehal, Drishti Library is part of Central government–led Bhashini initiative, the national mission aimed at building AI-driven language technologies for all Indian languages.

Bhashini’s core mandate – to strengthen OCR (a tech that converts images of the text into readable text), speech synthesis, and language tools for Indian languages – forms the technological backbone of Drishti. The library is built on OCR systems developed under a national consortium, aligned with Bhashini’s broader vision of inclusive, language-first digital public infrastructure.

“Any book in an Indian language can be scanned, proofread, converted, and finally made ready for Braille embossers or audio delivery,” said Prof Lehal.

The generated audio content is delivered through an audiobook reader application developed by the Product Lab at IIIT-H led by Prakash Yalla and Satish Kathirisetti, along with Meghana Tatavolu, Afrin Sayed, Sairam Bonu, Akhila Vennigalla and Vidushi Garg.

The application’s key features include adjustable playback speed, intuitive audio-based navigation controls, and accessibility-focused interface enhancements.

Despite progress, challenges such as achieving natural-sounding speech remain. “For some languages, we have very good TTS. However, for Punjabi, we found that high-quality text-to-speech is still missing. That will improve with time,” said Prof Lehal.

While the initial focus was generating content for UG and PG, the application scope widened with visually challenged students preparing for competitive exams demanding content for UPSC examinations, and the IIIT Hyderabad researchers are working in that direction.