NAACL 2022industry9 citations

Fast Bilingual Grapheme-To-Phoneme Conversion

Hwa-Yeon Kim, Jong-Hwan Kim, Jae-Min Kim

Abstract

Autoregressive transformer (ART)-based grapheme-to-phoneme (G2P) models have been proposed for bi/multilingual text-to-speech systems. Although they have achieved great success, they suffer from high inference latency in real-time industrial applications, especially processing long sentence. In this paper, we propose a fast and high-performance bilingual G2P model. For fast and exact decoding, we used a non-autoregressive structured transformer-based architecture and data augmentation for predicting output length. Our model achieved better performance than that of the previous autoregressive model and about 2700% faster inference speed.

BibTeX
@inproceedings{kim-etal-2022-fast,
    title = "Fast Bilingual Grapheme-To-Phoneme Conversion",
    author = "Kim, Hwa-Yeon  and
      Kim, Jong-Hwan  and
      Kim, Jae-Min",
    editor = "Loukina, Anastassia  and
      Gangadharaiah, Rashmi  and
      Min, Bonan",
    booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track",
    month = jul,
    year = "2022",
    address = "Hybrid: Seattle, Washington + Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.naacl-industry.32/",
    doi = "10.18653/v1/2022.naacl-industry.32",
    pages = "289--296"
}
Fast Bilingual Grapheme-To-Phoneme Conversion · NAACL 2022