mlsanityData to 14 Oct 2026

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

arXiv 2609.29146 ↗First posted 24 Sep 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 30 references that are in the map. First posted on arXiv 24 Sep 2026.

Builds on

16 of 30 references.

References · 16

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  2. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  3. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
  4. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  5. 2019LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speechcited by 649
  6. 2020ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verificationcited by 628
  7. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 561
  8. 2022BigVGAN: A Universal Neural Vocoder with Large-Scale Trainingcited by 251
  9. 2023StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Modelscited by 152
  10. 2023Matcha-TTS: A fast TTS architecture with conditional flow matchingcited by 145
  11. 2023Powerset multi-class cross entropy loss for neural speaker diarizationcited by 111
  12. 2021Towards Building ASR Systems for the Next Billion Userscited by 47
4 more
  1. 2022Towards Building Text-To-Speech Systems for the Next Billion Userscited by 27
  2. 2023VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Designcited by 25
  3. 2022Effectiveness of Mining Audio and Text Pairs from Public Data for Improving ASR Systems for Low-Resource Languagescited by 16
  4. 2022Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transformcited by 9

Built on by

Not cited yet.