International Journal of Computational Intelligence Systems

Volume 13, Issue 1, 2020, Pages 341 - 351

End-to-End Sequence Labeling via Convolutional Recurrent Neural Network with a Connectionist Temporal Classification Layer

Authors
Xiaohui Huang1, 2, *, Lisheng Qiao1, Wentao Yu2, Jing Li1, Yanzhou Ma2
1 College of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China
2 Zhengzhou Information Science and Technology Institute, Zhengzhou, Henan, China
*Corresponding author. Email: huangxia@mail.ustc.edu.cn
Corresponding Author
Xiaohui Huang
Received 23 September 2019, Accepted 12 March 2020, Available Online 20 March 2020.
DOI
https://doi.org/10.2991/ijcis.d.200316.001How to use a DOI?
Keywords
Sequence labeling, Convolutional recurrent neural network, Unified framework, End-to-end
Abstract

Sequence labeling is a common machine-learning task which not only needs the most likely prediction of label for a local input but also seeks the most suitable annotation for the whole input sequence. So it requires the model that is able to handle both the local spatial features and temporal-dependence features effectively. Furthermore, it is common for the length of the label sequence to be much shorter than the input sequence in some tasks such as speech recognition and handwritten text recognition. In this paper, we propose a kind of novel deep neural network architecture which combines convolution, pooling and recurrent in a unified framework to construct the convolutional recurrent neural network (CRNN) for sequence labeling tasks with variable lengths of input and output. Specifically, we design a novel CRNN to achieve the joint extraction of local spatial features and long-distance temporal-dependence features in sequence, introduce pooling along time to achieve a transform of long input to short output which will also reduce he model's complexity, and adopt Connectionist Temporal Classification (CTC) layer to achieve an end-to-end pattern for sequence labeling. Experiments on phoneme sequence recognition and handwritten character sequence recognition have been conducted and the results show that our method achieves great performance while having a more simplified architecture with more efficient training and labeling procedure.

Copyright
© 2020 The Authors. Published by Atlantis Press SARL.
Open Access
This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)
View full text (HTML)

Journal
International Journal of Computational Intelligence Systems
Volume-Issue
13 - 1
Pages
341 - 351
Publication Date
2020/03
ISSN (Online)
1875-6883
ISSN (Print)
1875-6891
DOI
https://doi.org/10.2991/ijcis.d.200316.001How to use a DOI?
Copyright
© 2020 The Authors. Published by Atlantis Press SARL.
Open Access
This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - JOUR
AU  - Xiaohui Huang
AU  - Lisheng Qiao
AU  - Wentao Yu
AU  - Jing Li
AU  - Yanzhou Ma
PY  - 2020
DA  - 2020/03
TI  - End-to-End Sequence Labeling via Convolutional Recurrent Neural Network with a Connectionist Temporal Classification Layer
JO  - International Journal of Computational Intelligence Systems
SP  - 341
EP  - 351
VL  - 13
IS  - 1
SN  - 1875-6883
UR  - https://doi.org/10.2991/ijcis.d.200316.001
DO  - https://doi.org/10.2991/ijcis.d.200316.001
ID  - Huang2020
ER  -