Homophone-based Label Smoothing in End-to-End Automatic Speech Recognition
This work addresses speech recognition accuracy for users of ASR systems, but it is incremental as it builds on existing label smoothing techniques with a specific linguistic twist.
The paper tackles the problem of improving end-to-end automatic speech recognition by proposing a homophone-based label smoothing method that incorporates pronunciation knowledge, resulting in a 0.4% absolute reduction in character error rate.
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.