Text to Speech System for Meitei Mayek Script

TL;DR

This paper develops a neural Text-to-Speech system for Manipuri language using Meitei Mayek script, adapting Tacotron 2 and HiFi-GAN to support tonal phonology and resource constraints, enabling natural speech synthesis.

Contribution

It introduces a novel neural TTS architecture tailored for Manipuri language and Meitei Mayek script, including phoneme mapping and dataset creation for under-resourced language support.

Findings

Achieved intelligible and natural speech synthesis.

Validated system with subjective and objective metrics.

Supports linguistic preservation and technological inclusion.

Abstract

This paper presents the development of a Text-to-Speech (TTS) system for the Manipuri language using the Meitei Mayek script. Leveraging Tacotron 2 and HiFi-GAN, we introduce a neural TTS architecture adapted to support tonal phonology and under-resourced linguistic environments. We develop a phoneme mapping for Meitei Mayek to ARPAbet, curate a single-speaker dataset, and demonstrate intelligible and natural speech synthesis, validated through subjective and objective metrics. This system lays the groundwork for linguistic preservation and technological inclusion of Manipuri.