BanglaKontho: Closing the Long-Form Gap in Bangla Text-to-Speech

Mizbaul Haque Maruf
9/24/2026
cs.CL

No confident code implementation found for this paper.

Abstract

Bangla, the seventh most spoken language in the world, remains under-resourced for neural text-to-speech. Public Bangla speech corpora are dominated by short read-prompt utterances collected for speech recognition, leaving long-form prosody and consistent single-speaker narration uncovered. We present BanglaKontho, a single-speaker Bangla TTS corpus of 20 hours derived from professional audiobook recordings: 7,050 segmented utterances with verified transcripts at 24 kHz. We also release a reusable Bangla text normalizer covering Bangladeshi-style digit grouping, currency and date expressions, Danda punctuation and Unicode normalization, together with the full preprocessing pipeline. An MB-iSTFT-VITS baseline trained from scratch reaches 9.5% WER and 4.46 naturalness MOS, against 16.0% and 3.16 for the same architecture retrained on the 12-hour IndicTTS-Bn corpus. The corpus is released openly under CC BY-NC 4.0.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

ClArTTS: An Open-Source Classical Arabic Text-to-Speech Corpus

89% match2023

Ramsa: A Large Sociolinguistically Rich Emirati Arabic Speech Corpus for ASR and TTS

87% match2026

Pashto Common Voice: Building the First Open Speech Corpus for a 60-Million-Speaker Low-Resource Language

87% match2026

BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpus

86% match1 repo132022

HK-LegiCoST: Leveraging Non-Verbatim Transcripts for Speech Translation

86% match2023

OpenBibleTTS: Large-Scale Speech Resources and TTS Models for Low-Resource Languages

86% match2026

Cite this paper

@article{maruf2026banglakontho,
  title  = {BanglaKontho: Closing the Long-Form Gap in Bangla Text-to-Speech},
  author = {Mizbaul Haque Maruf},
  year   = {2026},
  eprint = {2609.29146},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2609.29146v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2609.29146.svg)](https://codeofpaper.com/paper/2609.29146)

Discussion