MunTTS: A Text-to-Speech System for Mundari
This work addresses the problem of linguistic technology gaps for underrepresented languages like Mundari, though it is incremental as it applies existing TTS methods to a new language.
The researchers tackled the lack of text-to-speech technology for Mundari, a low-resource language, by developing MunTTS, an end-to-end system that was evaluated with native speakers and objective metrics, showing its potential for language preservation.
We present MunTTS, an end-to-end text-to-speech (TTS) system specifically for Mundari, a low-resource Indian language of the Austo-Asiatic family. Our work addresses the gap in linguistic technology for underrepresented languages by collecting and processing data to build a speech synthesis system. We begin our study by gathering a substantial dataset of Mundari text and speech and train end-to-end speech models. We also delve into the methods used for training our models, ensuring they are efficient and effective despite the data constraints. We evaluate our system with native speakers and objective metrics, demonstrating its potential as a tool for preserving and promoting the Mundari language in the digital age.