Tezpur University has embarked on an innovative mission to safeguard the endangered Rabha and Tiwa languages by combining artificial intelligence with traditional linguistic expertise. The initiative, led by the Department of Linguistics and Language Technology, seeks to digitally document, analyse, and revitalise these rich indigenous languages spoken across Assam.

The project is designed to build advanced language datasets and develop tools that can support modern-day applications such as translation systems, speech recognition, and online learning modules. By using AI-based Parts-of-Speech tagging and other natural-language-processing techniques, the university aims to ensure these languages gain a stronger foothold in the digital world.

As part of the first phase, Tezpur University recently conducted an intensive five-day workshop focused on data collection and annotation. The workshop brought together tribal scholars, community members, and academic experts to collaboratively gather authentic linguistic samples and standardise grammatical structures. This participatory model places local communities at the heart of the process, ensuring both cultural accuracy and ownership.

“Preserving indigenous languages is a race against time,” said Dr Arup Kumar Nath, who leads the project. “By building digital foundations today, we are giving these languages a future in classrooms, on devices, and in public discourse.”

The initiative complements national and global efforts to promote linguistic diversity and inclusive technology. With continued collaboration between academia, government, and local communities, Tezpur University aims to develop open digital resources that can be used for education, AI research, and cultural preservation — ensuring that the voices of the Rabha and Tiwa people remain vibrant for generations to come.