Papers
Topics
Authors
Recent
Search
2000 character limit reached

VoxHakka: A Dialectally Diverse Multi-speaker Text-to-Speech System for Taiwanese Hakka

Published 3 Sep 2024 in cs.SD, cs.AI, cs.CL, and eess.AS | (2409.01548v3)

Abstract: This paper introduces VoxHakka, a text-to-speech (TTS) system designed for Taiwanese Hakka, a critically under-resourced language spoken in Taiwan. Leveraging the YourTTS framework, VoxHakka achieves high naturalness and accuracy and low real-time factor in speech synthesis while supporting six distinct Hakka dialects. This is achieved by training the model with dialect-specific data, allowing for the generation of speaker-aware Hakka speech. To address the scarcity of publicly available Hakka speech corpora, we employed a cost-effective approach utilizing a web scraping pipeline coupled with automatic speech recognition (ASR)-based data cleaning techniques. This process ensured the acquisition of a high-quality, multi-speaker, multi-dialect dataset suitable for TTS training. Subjective listening tests conducted using comparative mean opinion scores (CMOS) demonstrate that VoxHakka significantly outperforms existing publicly available Hakka TTS systems in terms of pronunciation accuracy, tone correctness, and overall naturalness. This work represents a significant advancement in Hakka language technology and provides a valuable resource for language preservation and revitalization efforts.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (13)
  1. “Transfer learning from speaker verification to multispeaker text-to-speech synthesis,” in Proc. NeurIPS, 2018.
  2. “YourTTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone,” in Proc. ICML, 2022.
  3. “Neural codec language models are zero-shot text to speech synthesizers,” in Arxiv preprint arXiv:2301.02111, 2023.
  4. “XTTS: A massively multilingual zero-shot text-to-speech model,” in Proc. Interspeech, 2024.
  5. “CLaM-TTS: Improving neural codec language model for zero-shot text-to-speech,” in Proc. ICLR, 2024.
  6. “The Kaldi speech recognition toolkit,” in Proc. ASRU, 2011.
  7. “Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech,” in Proc. ICML, 2021.
  8. “Clova baseline system for the VoxCeleb speaker recognition challenge 2020,” in Arxiv preprint arXiv:2009.14153, 2020.
  9. “WaveNet: A generative model for raw audio,” in Proc. SSW, 2016.
  10. “HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis,” in Proc. NeurIPS, 2020.
  11. “Auto-encoding variational Bayes,” in ICLR, 2014.
  12. “Decoupled weight decay regularization,” in Proc. ICLR, 2019.
  13. “Taiwanese Hakka across Taiwan corpus and Formosa speech recognition challenge 2023 - Hakka ASR,” in Proc. O-COCOSDA, 2023.

Summary

No one has generated a summary of this paper yet.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Collections

Sign up for free to add this paper to one or more collections.