Homophone-based Label Smoothing in End-to-End Automatic Speech Recognition
arXiv:2004.03437
Abstract
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.
References in corpus (5)
- Distilling the Knowledge in a Neural Network
- Attention-Based Models for Speech Recognition
- Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition
- ESPnet: End-to-End Speech Processing Toolkit
- CLUECorpus2020: A Large-scale Chinese Corpus for Pre-training Language Model