@inproceedings{senyk-etal-2025-context,
    title = "Context-Aware Lexical Stress Prediction and Phonemization for {U}krainian {TTS} Systems",
    author = "Senyk, Anastasiia  and
      Lukianchuk, Mykhailo  and
      Robeiko, Valentyna  and
      Paniv, Yurii",
    editor = "Romanyshyn, Mariana",
    booktitle = "Proceedings of the Fourth Ukrainian Natural Language Processing Workshop (UNLP 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria (online)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.unlp-1.11/",
    pages = "96--104",
    ISBN = "979-8-89176-269-5",
    abstract = "Text preprocessing is a fundamental component of high-quality speech synthesis. This work presents a novel rule-based phonemizer combined with a sentence-level lexical stress prediction model to improve phonetic accuracy and prosody prediction in the text-to-speech pipelines. We also introduce a new benchmark dataset with annotated stress patterns designed for evaluating lexical stress prediction systems at the sentence level.Experimental results demonstrate that the proposed phonemizer achieves a 1.23{\%} word error rate on a manually constructed pronunciation dataset, while the lexical stress prediction pipeline shows results close to dictionary-based methods, outperforming existing neural network solutions."
}