@inproceedings{geng-etal-2025-scaling,
    title = "Scaling Under-Resourced {TTS}: A Data-Optimized Framework with Advanced Acoustic Modeling for {T}hai",
    author = "Geng, Yizhong  and
      Xu, Jizhuo  and
      Liang, Zeyu  and
      Yang, Jinghan  and
      Shi, Xiaoyi  and
      Shen, Xiaoyu",
    editor = "Rehm, Georg  and
      Li, Yunyao",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/mtsummit-25-ingestion/2025.acl-industry.42/",
    doi = "10.18653/v1/2025.acl-industry.42",
    pages = "593--604",
    ISBN = "979-8-89176-288-6",
    abstract = "Text-to-speech (TTS) technology has achieved impressive results for widely spoken languages, yet many under-resourced languages remain challenged by limited data and linguistic complexities. In this paper, we present a novel methodology that integrates a data-optimized framework with an advanced acoustic model to build high-quality TTS systems for low-resource scenarios. We demonstrate the effectiveness of our approach using Thai as an illustrative case, where intricate phonetic rules and sparse resources are effectively addressed. Our method enables zero-shot voice cloning and improved performance across diverse client applications, ranging from finance to healthcare, education, and law. Extensive evaluations{---}both subjective and objective{---}confirm that our model meets state-of-the-art standards, offering a scalable solution for TTS production in data-limited settings, with significant implications for broader industry adoption and multilingual accessibility. All demos are available in \url{https://luoji.cn/static/thai/demo.html}."
}