@inproceedings{chu-etal-2020-learning,
    title = "{L}earning to {P}ronounce {C}hinese {W}ithout a {P}ronunciation {D}ictionary",
    author = "Chu, Christopher  and
      Fang, Scot  and
      Knight, Kevin",
    editor = "Webber, Bonnie  and
      Cohn, Trevor  and
      He, Yulan  and
      Liu, Yang",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.emnlp-main.458/",
    doi = "10.18653/v1/2020.emnlp-main.458",
    pages = "5687--5693",
    abstract = "We demonstrate a program that learns to pronounce Chinese text in Mandarin, without a pronunciation dictionary. From non-parallel streams of Chinese characters and Chinese pinyin syllables, it establishes a many-to-many mapping between characters and pronunciations. Using unsupervised methods, the program effectively deciphers writing into speech. Its token-level character-to-syllable accuracy is 89{\%}, which significantly exceeds the 22{\%} accuracy of prior work."
}