Khasi Language Learning and Phonetic Database Creation

Abstract

The Khasi language, spoken by the indigenous Khasi people of Meghalaya, India, is a unique and vibrant part of the Austroasiatic language family, but lacks digital resources for learning and documentation. This project proposes to create a phonetic database and language learning tools for Khasi, employing both bottom-up (phonetic) and top-down (vocabulary-based) approaches. This dual approach is grounded in research on language acquisition, which emphasises the importance of both phonetic understanding and vocabulary building. A review of existing literature reveals a gap in comprehensive phonetic resources for Khasi, despite recent advancements in language processing tools and the availability of translated texts. This project aims to fill this gap by building upon existing resources and incorporating phonetic transcriptions and audio recordings. The project will achieve its goals by enhancing existing Khasi word datasets, identifying high-frequency words, creating a phonetic database similar to the "Oxford 3000" for English, and developing a mobile app and web-based dashboard for language learning. The project deliverables include an enhanced Khasi word dataset, a high-frequency word list, a phonetic database, and user-friendly language learning tools. By creating these resources, this project will empower both native speakers and learners of Khasi to engage with and preserve the language's rich linguistic heritage. It will also contribute to the development of more accurate language processing tools and promote the revitalisation of the Khasi language in the digital age.

Last updated on 23rd May, 2025