Biddwan Ahmed


2024

pdf bib
Bahasa Harmony: A Comprehensive Dataset for Bahasa Text-to-Speech Synthesis with Discrete Codec Modeling of EnGen-TTS.
Onkar Susladkar | Vishesh Tripathi | Biddwan Ahmed
Findings of the Association for Computational Linguistics: EMNLP 2024

This research introduces a comprehensive Bahasa text-to-speech (TTS) dataset and a novel TTS model, EnGen-TTS, designed to enhance the quality and versatility of synthetic speech in the Bahasa language. The dataset, spanning 55.00 hours and 52K audio recordings, integrates diverse textual sources, ensuring linguistic richness. A meticulous recording setup captures the nuances of Bahasa phonetics, employing professional equipment to ensure high-fidelity audio samples. Statistical analysis reveals the dataset’s scale and diversity, laying the foundation for model training and evaluation. The proposed EnGen-TTS model performs better than established baselines, achieving a Mean Opinion Score (MOS) of 4.45 ± 0.13. Additionally, our investigation on real-time factor and model size highlights EnGen-TTS as a compelling choice, with efficient performance. This research marks a significant advancement in Bahasa TTS technology, with implications for diverse language applications.