BnTTS: Few-Shot Speaker Adaptation in Low-Resource Setting
Mohammad Jahid Ibna Basher, Md Kowsher, Md Saiful Islam, Rabindra Nath Nandi, Nusrat Jahan Prottasha, Mehadi Hasan Menon, Tareq Al Muntasir, Shammur Absar Chowdhury
Abstract
This paper introduces BnTTS (Bangla Text-To-Speech), the first framework for Bangla speaker adaptation-based TTS, designed to bridge the gap in Bangla speech synthesis using minimal training data. Building upon the XTTS architecture, our approach integrates Bangla into a multilingual TTS pipeline, with modifications to account for the phonetic and linguistic characteristics of the language. We pretrain BnTTS on 3.85k hours of Bangla speech dataset with corresponding text labels and evaluate performance in both zero-shot and few-shot settings on our proposed test dataset. Empirical evaluations in few-shot settings show that BnTTS significantly improves the naturalness, intelligibility, and speaker fidelity of synthesized Bangla speech. Compared to state-of-the-art Bangla TTS systems, BnTTS exhibits superior performance in Subjective Mean Opinion Score (SMOS), Naturalness, and Clarity metrics.
BibTeX
@inproceedings{basher-etal-2025-bntts,
title = "{B}n{TTS}: Few-Shot Speaker Adaptation in Low-Resource Setting",
author = "Basher, Mohammad Jahid Ibna and
Kowsher, Md and
Islam, Md Saiful and
Nandi, Rabindra Nath and
Prottasha, Nusrat Jahan and
Menon, Mehadi Hasan and
Muntasir, Tareq Al and
Chowdhury, Shammur Absar and
Alam, Firoj and
Yousefi, Niloofar and
Garibay, Ozlem",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.279/",
pages = "4956--4968",
ISBN = "979-8-89176-195-7"
}