Phonetic Completeness Over Prosodic Diversity: Syllable-Level Synthetic Corpus Construction for Low-Resource Penang Hokkien Speech Synthesis
International Journal of Advanced Computer Science and Applications · 2026 · 17 (5)
DOI: 10.14569/ijacsa.2026.0170563 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Advanced Computer Science and Applications, 2026. Verfasst von Yu Liang Lai und 3 weiteren Autor:innen.
Abstract (Originalsprache)
This study presents the first Text-to-Speech (TTS) model for Penang Hokkien, a low-resource tonal dialect at risk of extinction. To address phonological sparsity in the collected speech corpus, we propose a two-stage fine-tuning approach that emphasizes comprehensive phonetic coverage through syllable-level synthetic augmentation while subsequently refining prosodic naturalness using real speech recordings. By supplementing a limited 45-minute real speech corpus with a 2-hour syllable-level concatenative synthetic corpus, the full dialectal inventory of approximately 2,000 unique syllable-tone combinations was encompassed. Experimental results suggest that improving syllable-tone coverage contributes substantially to intelligibility and tonal accuracy in this low-resource tonal setting. Technical optimizations, including a 600-ms cross-fading technique to mitigate boundary artifacts and numerical tone markers to reduce token sparsity, further improved model stability and synthesis quality. The final model achieved a Mean Opinion Score (MOS) of 3.92.
Zitieren
APA
Lai, Y. L., Khaw, Y. M. J., Lim, S. P., & Tan, T. P. (2026). Phonetic Completeness Over Prosodic Diversity: Syllable-Level Synthetic Corpus Construction for Low-Resource Penang Hokkien Speech Synthesis. International Journal of Advanced Computer Science and Applications, 17(5). https://doi.org/10.14569/ijacsa.2026.0170563
Vancouver
Lai YL, Khaw YMJ, Lim SP, Tan TP. Phonetic Completeness Over Prosodic Diversity: Syllable-Level Synthetic Corpus Construction for Low-Resource Penang Hokkien Speech Synthesis. International Journal of Advanced Computer Science and Applications. 2026;17(5). doi:10.14569/ijacsa.2026.0170563
BibTeX
@article{Lai2026,
author = {Lai, Yu Liang and Khaw, Yen Min Jasmina and Lim, Seng Poh and Tan, Tien Ping},
title = {Phonetic Completeness Over Prosodic Diversity: Syllable-Level Synthetic Corpus Construction for Low-Resource Penang Hokkien Speech Synthesis},
journal = {International Journal of Advanced Computer Science and Applications},
year = {2026},
volume = {17},
number = {5},
doi = {10.14569/ijacsa.2026.0170563}
}
EUVIMED