← Search

Yuxiang Zou

1 accepted papers

2023

LiteG2P: A Fast, Light and High Accuracy Model for Grapheme-to-Phoneme Conversion

ICASSP 2023accepted

As a key component of automated speech recognition (ASR) and the front-end in text-to-speech (TTS), grapheme-to-phoneme (G2P) plays the role of converting letters to their corresponding pronunciations. Existing methods are either slow or poor in performance, and are limited in application scenarios,…

Cited by 0SourceScholar