This study addresses robust automatic speech recognition (ASR) by introducing
a Conformer-based acoustic model. The proposed model builds on the wide
residual bi-directional long short-term memory network (WRBN) with
utterance-wise dropout and iterative speaker adaptation, but employs a
Conformer encoder instead of the recurrent network. The Conformer encoder uses
a convolution-augmented attention mechanism for acoustic modeling. The proposed
system is evaluated on the monaural ASR task of the CHiME-4 corpus. Coupled
with utterance-wise normalization and speaker adaptation, our model achieves
$6.25\%$ word error rate, which outperforms WRBN by $8.4\%$ relatively. In
addition, the proposed Conformer-based model is $18.3\%$ smaller in model size
and reduces total training time by $79.6\%$.

本研究采用基于 Conformer 的声学模型解决了自动语音识别中的鲁棒性问题，并在 CHiME-4 语料库的单声道 ASR 任务中经过测试，其使用 utterance-wise 归一化和说话人自适应的方式，相比经典的 wide residual 双向长短时记忆网络，减小了 18.3% 的模型大小，训练时间减少了 79.6％且相对误差率比 WRBN 低 8.4%。