# Recurrent neural network transducer for Japanese and Chinese offline handwritten text recognition

arXiv: https://arxiv.org/abs/2106.14459 · HTML: https://mlsanity.com/paper/2106.14459/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 30 references that are in the map.
- First posted on arXiv 28 Jun 2021.

## Builds on (most cited first, 6 of 6)

- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Deep Learning for Classical Japanese Literature](https://mlsanity.com/paper/1812.01718/) (2018)
- [Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning](https://mlsanity.com/paper/1609.06773/) (2016)
- [End-to-End Attention-based Large Vocabulary Speech Recognition](https://mlsanity.com/paper/1508.04395/) (2015)
- [Scan, Attend and Read: End-to-End Handwritten Paragraph Recognition with MDLSTM Attention](https://mlsanity.com/paper/1604.03286/) (2016)
- [A Scalable Handwritten Text Recognition System](https://mlsanity.com/paper/1904.09150/) (2019)

## Built on by (most cited first, 2 of 2)

- [KOHTD: Kazakh Offline Handwritten Text Dataset](https://mlsanity.com/paper/2110.04075/) (2021)
- [Improving Handwritten Text Recognition via 3D Attention and Multi-Scale Training](https://mlsanity.com/paper/2410.18374/) (2024)

## Abstract (arXiv)

In this paper, we propose an RNN-Transducer model for recognizing Japanese and Chinese offline handwritten text line images. As far as we know, it is the first approach that adopts the RNN-Transducer model for offline handwritten text recognition. The proposed model consists of three main components: a visual feature encoder that extracts visual features from an input image by CNN and then encodes the visual features by BLSTM; a linguistic context encoder that extracts and encodes linguistic features from the input image by embedded layers and LSTM; and a joint decoder that combines and then decodes the visual features and the linguistic features into the final label sequence by fully connected and softmax layers. The proposed model takes advantage of both visual and linguistic information from the input image. In the experiments, we evaluated the performance of the proposed model on the two datasets: Kuzushiji and SCUT-EPT. Experimental results show that the proposed model achieves state-of-the-art performance on all datasets.