Jae-Min Kim


2022

pdf
Fast Bilingual Grapheme-To-Phoneme Conversion
Hwa-Yeon Kim | Jong-Hwan Kim | Jae-Min Kim
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track

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.