This paper describes a novel training method for acoustic models using connectionist temporal classification (CTC) for Japanese end-to-end automatic speech recognition (ASR). End-to-end ASR can estimate characters directly without using a pronunciation dictionary; however, this approach was conducted mostly in the English research area. When dealing with languages such as Japanese, we confront difficulties with robust acoustic modeling. One of the issues is caused by a large number of characters, including Japanese kanji, which leads to an increase in the number of model parameters. Additionally, multiple pronunciations of kanji increase the variance of acoustic features for corresponding characters. Therefore, we propose end-to-end ASR based on bi-directional long short-term memory (BLSTM) networks to solve these problems. Our proposal involves two approaches: reducing the number of dimensions of BLSTM and adding character strings to output layer labels. Dimensional compression decreases the number of parameters, while output label expansion reduces the variance of acoustic features. Consequently, we could obtain a robust model with a small number of parameters. Our experimental results with Japanese broadcast programs show the combined method of these two approaches improved the word error rate significantly compared with the conventional character-based end-to-end approach.