@inproceedings{peng-2026-g,
    title = "{G}{\&}{P}2{P}: A Multi-Source Approach to Grapheme-to-Phoneme Conversion",
    author = "Peng, Chun-Yi Jerry",
    editor = "Gorman, Kyle",
    booktitle = "Proceedings of the Third Workshop on Computation and Written Language ({CAWL} 2026) @ {LREC} 2026",
    month = jun,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/revision-workflow/2026.cawl-1.9/",
    doi = "10.63317/4f2x3fda6jj7",
    pages = "89--94",
    abstract = "Grapheme-to-phoneme (G2P) conversion plays a central role in speech technologies. This paper introduces G{\&}P2P, a multi-source framework that integrates multiple pronunciation dictionaries to enhance G2P modeling. We evaluate both expert-curated and crowd-sourced resources using attentive LSTM, pointer-generator LSTM, and transformer architectures. Results indicate that combining high-quality expert dictionaries yields substantial improvements, achieving an 11.26-point absolute (22{\%} relative) reduction in word error rate. In contrast, incorporating noisy crowd-sourced resources may degrade performance. Statistical analyses further suggest that dataset quality exerts a greater influence on outcomes than the choice of fusion strategy, offering practical guidance for the design of multi-source G2P systems."
}