BanglaTTS gets improved quality and long-form speech dataset
BanglaKontho: Closing the Long-Form Gap in Bangla Text-to-Speech
Computation and Language
Summary
Bangla is a widely spoken language but lacks good tools to turn written text into natural speech, especially for long passages. The authors provide a new collection of 20 hours of professionally recorded Bangla audiobook speech as a dataset for building such systems. They also offer software to clean and prepare Bangla text for speech synthesis. Their baseline system trained on this new data speaks more naturally and accurately compared to previous smaller datasets.
What this means in practice
- •For voice assistant developers: Build Bangla text-to-speech systems that generate natural and consistent narration in long-form content using this new dataset and tools.$Commercial implications: Enables commercial Bangla audiobook and voice assistant products needing high-quality and long-form narration.
- •For multilingual tts system builders: Extend existing text-to-speech platforms with better Bangla support by leveraging the open BanglaKontho dataset and text normalization pipeline.
Authors
Mizbaul Haque Maruf
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.