mlsanityData to 7 Oct 2026

BnTTS: Few-Shot Speaker Adaptation in Low-Resource Setting

arXiv 2502.05729 ↗First posted 9 Feb 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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 pre-train 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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 37 references that are in the map. First posted on arXiv 9 Feb 2025.

Builds on

14 of 37 references.

References · 14

  1. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  2. 2023Powerset multi-class cross entropy loss for neural speaker diarizationcited by 109
  3. 2019Music Source Separation in the Waveform Domaincited by 98
  4. 2021Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generationcited by 93
  5. 2021SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Modelcited by 56
  6. 2021VoiceFixer: Toward General Speech Restoration with Neural Vocodercited by 50
  7. 2024SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metricscited by 38
  8. 2022Towards Building Text-To-Speech Systems for the Next Billion Userscited by 27
  9. 2024ECAPA2: A Hybrid Neural Network Architecture and Training Strategy for Robust Speaker Embeddingscited by 22
  10. 2020Transfer Learning from Speech Synthesis to Voice Conversion with Non-Parallel Training Datacited by 17
  11. 2020Generic Indic Text-to-speech Synthesisers with Rapid Adaptation in an End-to-end Frameworkcited by 9
  12. 2023Pseudo-Labeling for Domain-Agnostic Bangla Automatic Speech Recognitioncited by 4
2 more
  1. 2024An Initial Investigation of Language Adaptation for TTS Systems under Low-resource Scenarioscited by 4
  2. 2020Learning to Maximize Speech Quality Directly Using MOS Prediction for Neural Text-to-Speechcited by 1

Built on by

Not cited yet.