Much of the recent literature on automatic speech recognition (ASR) is taking an end-to-end approach. Unlike English where the writing system is closely related to sound, Chinese characters (Hanzi) represent meaning, not sound. We propose factoring audio -> Hanzi into two sub-tasks: (1) audio -> Pinyin and (2) Pinyin -> Hanzi, where Pinyin is a system of phonetic transcription of standard Chinese. Factoring the audio -> Hanzi task in this way achieves 3.9% CER (character error rate) on the Aishell-1 corpus, the best result reported on this dataset so far.
@article{arxiv.2108.01129,
title = {Decoupling recognition and transcription in Mandarin ASR},
author = {Jiahong Yuan and Xingyu Cai and Dongji Gao and Renjie Zheng and Liang Huang and Kenneth Church},
journal= {arXiv preprint arXiv:2108.01129},
year = {2021}
}