Connectionist temporal classification (CTC) and attention-based encoder
decoder (AED) joint training has been widely applied in automatic speech
recognition (ASR). Unlike most hybrid models that separately calculate the CTC
and AED losses, our proposed integrated-CTC utilizes the attention mechanism of
AED to guide the output of CTC. In this paper, we employ two fusion methods,
namely direct addition of logits (DAL) and preserving the maximum probability
(PMP). We achieve dimensional consistency by adaptively affine transforming the
attention results to match the dimensions of CTC. To accelerate model
convergence and improve accuracy, we introduce auxiliary loss regularization
for accelerated convergence. Experimental results demonstrate that the DAL
method performs better in attention rescoring, while the PMP method excels in
CTC prefix beam search and greedy search.

本文介绍了连接主义时间分类（CTC）和基于注意力的编码器解码器（AED）联合训练在自动语音识别（ASR）中的应用，提出了两种融合方法，即 logits 的直接相加（DAL）和最大概率的保留（PMP），并引入辅助损失正则化以加速模型收敛和提高准确性。实验结果表明，DAL 方法在注意力修正方面效果更好，而 PMP 方法在 CTC 前缀搜索和贪婪搜索方面表现出色。