A new label smoothing method that makes use of prior knowledge of a language at human level, homophone, is proposed in this paper for automatic speech recognition (ASR). Compared with its forerunners, the proposed method uses pronunciation knowledge of homophones in a more complex way. End-to-end ASR models that learn acoustic model and language model jointly and modelling units of characters are necessary conditions for this method. Experiments with hybrid CTC sequence-to-sequence model show that the new method can reduce character error rate (CER) by 0.4% absolutely.
@article{arxiv.2004.03437,
title = {Homophone-based Label Smoothing in End-to-End Automatic Speech Recognition},
author = {Yi Zheng and Xianjie Yang and Xuyong Dang},
journal= {arXiv preprint arXiv:2004.03437},
year = {2020}
}