Neural network language models for off-line handwriting recognition |
| |
Authors: | F. Zamora-Martí nez,V. Frinken,S. Españ a-Boquera,M.J. Castro-Bleda,A. Fischer,H. Bunke |
| |
Affiliation: | 1. Escuela de Enseñanzas Técnicas, Departamento de Ciencias Físicas, Matemáticas y de la Computación, Universidad CEU Cardenal Herrera, C/San Bartolomé 55, 46155 Alfara del Patriarca, Valencia, Spain;2. Departamento de Sistemas Informáticos y Computación, Universitat Politècnica de València, Valencia, Spain;3. Faculty of Information Science and Electrical Engineering, Kyushu University, Japan;4. Institute for Computer Science and Applied Mathematics, University of Bern, Bern, Switzerland |
| |
Abstract: | Unconstrained off-line continuous handwritten text recognition is a very challenging task which has been recently addressed by different promising techniques. This work presents our latest contribution to this task, integrating neural network language models in the decoding process of three state-of-the-art systems: one based on bidirectional recurrent neural networks, another based on hybrid hidden Markov models and, finally, a combination of both. Experimental results obtained on the IAM off-line database demonstrate that consistent word error rate reductions can be achieved with neural network language models when compared with statistical N-gram language models on the three tested systems. The best word error rate, 16.1%, reported with ROVER combination of systems using neural network language models significantly outperforms current benchmark results for the IAM database. |
| |
Keywords: | Handwritten text recognition (HTR) Language models (LMs) Neural networks (NNs) Neural network language model (NN LM) Bidirectional long short-term memory neural networks (BLSTM) Hybrid HMM/ANN models ROVER combination |
本文献已被 ScienceDirect 等数据库收录! |
|