论文标题
端到端自动语音识别中基于同型标签平滑
Homophone-based Label Smoothing in End-to-End Automatic Speech Recognition
论文作者
论文摘要
本文提出了一种新的标签平滑方法，该方法利用人类层面的语言知识，在本文中提议自动语音识别（ASR）。与其先驱者相比，提出的方法以更复杂的方式使用同型词的发音知识。共同学习声学模型和语言模型的端到端ASR模型以及字符的建模单位是此方法的必要条件。混合CTC序列到序列模型的实验表明，新方法可以将角色错误率（CER）降低0.4％。
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.
