End-to-end automatic speech recognition directly maps input speech to
characters. However, the mapping can be problematic when several different
pronunciations should be mapped into one character or when one pronunciation is
shared among many different characters. Japanese ASR suffers the most from such
many-to-one and one-to-many mapping problems due to Japanese kanji characters.
To alleviate the problems, we introduce explicit interaction between characters
and syllables using Self-conditioned connectionist temporal classification
(CTC), in which the upper layers are ``self-conditioned'' on the intermediate
predictions from the lower layers. The proposed method utilizes character-level
and syllable-level intermediate predictions as conditioning features to deal
with mutual dependency between characters and syllables. Experimental results
on Corpus of Spontaneous Japanese show that the proposed method outperformed
the conventional multi-task and Self-conditioned CTC methods.

该研究介绍了一种解决日语 ASR 中多对一和一对多映射问题的方法，使用 Self-conditioned connectionist temporal classification 让字符和音节之间进行显式互动，利用字符和音节的中间预测结果作为条件特征处理字符和音节之间的相互依存关系，并在 Corpus of Spontaneous Japanese 上得到了较好的实验结果。