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.

中文翻译：

---

端到端自动语音识别中基于同音字的标签平滑

本文提出了一种新的标签平滑方法，该方法利用人类级别语言的先验知识，同音字，用于自动语音识别 (ASR)。与其前身相比，所提出的方法以更复杂的方式使用了同音字的发音知识。联合学习声学模型和语言模型的端到端 ASR 模型以及对字符进行建模是该方法的必要条件。混合 CTC 序列到序列模型的实验表明，新方法可以将字符错误率 (CER) 绝对降低 0.4%。