The Digital India BHASHINI Division and the Indian Institute of Science (IISc), Bengaluru, have developed text-to-speech (TTS) models for Sourashtra, a minority Indo-Aryan language spoken predominantly by the Sourashtra community in Tamil Nadu. The Ministry of Electronics and Information Technology said the initiative aims to expand the availability of speech technology for languages with limited digital resources. It will also support the use of these languages in digital applications, language learning, accessibility solutions, documentation, and research. According to the Ministry, the newly developed models use a Variational Inference with Adversarial Learning-based end-to-end text-to-speech architecture, enabling them to generate Sourashtra speech directly from text. The models feature both male and female voices, with each voice supporting text written in both Tamil and Sourashtra scripts. This enables users to access and use Sourashtra in the scripts commonly used to write the language.
Must Read
- Advertisement -
