Saved in:
Bibliographic Details
Main Authors: Susladkar, Onkar Kishor, Tripathi, Vishesh, Ahmed, Biddwan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.06608
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910641835474944
author Susladkar, Onkar Kishor
Tripathi, Vishesh
Ahmed, Biddwan
author_facet Susladkar, Onkar Kishor
Tripathi, Vishesh
Ahmed, Biddwan
contents 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 \textasciitilde55.0 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 $\pm$ 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. Link to Generated Samples: \url{https://bahasa-harmony-comp.vercel.app/}
format Preprint
id arxiv_https___arxiv_org_abs_2410_06608
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Bahasa Harmony: A Comprehensive Dataset for Bahasa Text-to-Speech Synthesis with Discrete Codec Modeling of EnGen-TTS
Susladkar, Onkar Kishor
Tripathi, Vishesh
Ahmed, Biddwan
Sound
Artificial Intelligence
Audio and Speech Processing
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 \textasciitilde55.0 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 $\pm$ 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. Link to Generated Samples: \url{https://bahasa-harmony-comp.vercel.app/}
title Bahasa Harmony: A Comprehensive Dataset for Bahasa Text-to-Speech Synthesis with Discrete Codec Modeling of EnGen-TTS
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2410.06608