The recent emergence of joint CTC-Attention model shows significant
improvement in automatic speech recognition (ASR). The improvement largely lies
in the modeling of linguistic information by decoder. The decoder
joint-optimized with an acoustic encoder renders the language model from
ground-truth sequences in an auto-regressive manner during training. However,
the training corpus of the decoder is limited to the speech transcriptions,
which is far less than the corpus needed to train an acceptable language model.
This leads to poor robustness of decoder. To alleviate this problem, we propose
linguistic-enhanced transformer, which introduces refined CTC information to
decoder during training process, so that the decoder can be more robust. Our
experiments on AISHELL-1 speech corpus show that the character error rate (CER)
is relatively reduced by up to 7%. We also find that in joint CTC-Attention ASR
model, decoder is more sensitive to linguistic information than acoustic
information.

本文介绍了一种基于联合 CTC-Attention 模型的改进方法 —— 语言增强变压器，它通过在训练过程中将改进的 CTC 信息引入解码器，从而使其更加鲁棒，在 AISHELL-1 语音语料库上的实验表明，字符误差率（CER）减少了高达 7％，同时发现在联合 CTC-Attention ASR 模型中，解码器对语言信息比声学信息更敏感。