Handwriting Recognition with Large Multidimensional Long Short-Term Memory Recurrent Neural Networks

被引：0
|
作者：
Voigtlaender, Paul [1 ]
Doetsch, Patrick [1 ]
Ney, Hermann [1 ]
机构：
[1] Rhein Westfal TH Aachen, Human Language Technol & Pattern Recognit, Dept Comp Sci, D-52056 Aachen, Germany
来源：
PROCEEDINGS OF 2016 15TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR) | 2016年
关键词：
MDLSTM; LSTM; Long Short -Term Memory; Recurrent Neural Network; Handwriting Recognition;
D O I：
10.1109/ICFHR.2016.48
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Multidimensional long short-term memory recurrent neural networks achieve impressive results for handwriting recognition. However, with current CPU-based implementations, their training is very expensive and thus their capacity has so far been limited. We release an efficient GPU-based implementation which greatly reduces training times by processing the input in a diagonal-wise fashion. We use this implementation to explore deeper and wider architectures than previously used for handwriting recognition and show that especially the depth plays an important role. We outperform state of the art results on two databases with a deep multidimensional network.
引用
收藏
页码：228 / 233
页数：6
相关论文
共 50 条
  • [1] Long Short-Term Memory based Convolutional Recurrent Neural Networks for Large Vocabulary Speech Recognition
    Li, Xiangang
    Wu, Xihong
    [J]. 16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 3219 - 3223
  • [2] BIDIRECTIONAL QUATERNION LONG SHORT-TERM MEMORY RECURRENT NEURAL NETWORKS FOR SPEECH RECOGNITION
    Parcollet, Titouan
    Morchid, Mohamed
    Linares, Georges
    De Mori, Renato
    [J]. 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 8519 - 8523
  • [3] An analysis of Convolutional Long Short-Term Memory Recurrent Neural Networks for gesture recognition
    Tsironi, Eleni
    Barros, Pablo
    Weber, Cornelius
    Wermter, Stefan
    [J]. NEUROCOMPUTING, 2017, 268 : 76 - 86
  • [4] CONSTRUCTING LONG SHORT-TERM MEMORY BASED DEEP RECURRENT NEURAL NETWORKS FOR LARGE VOCABULARY SPEECH RECOGNITION
    Li, Xianggang
    Wu, Xihong
    [J]. 2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP), 2015, : 4520 - 4524
  • [5] Long-Short Term Memory Neural Networks Language Modeling for Handwriting Recognition
    Frinken, Volkmar
    Zamora-Martinez, Francisco
    Espana-Boquera, Salvador
    Jose Castro-Bleda, Maria
    Fischer, Andreas
    Bunke, Horst
    [J]. 2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012), 2012, : 701 - 704
  • [6] On Speaker Adaptation of Long Short-Term Memory Recurrent Neural Networks
    Miao, Yajie
    Metze, Florian
    [J]. 16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 1101 - 1105
  • [7] Long Short-Term Memory Recurrent Neural Network for Automatic Speech Recognition
    Oruh, Jane
    Viriri, Serestina
    Adegun, Adekanmi
    [J]. IEEE ACCESS, 2022, 10 : 30069 - 30079
  • [8] Simplified Gating in Long Short-term Memory (LSTM) Recurrent Neural Networks
    Lu, Yuzhen
    Salem, Fathi M.
    [J]. 2017 IEEE 60TH INTERNATIONAL MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS (MWSCAS), 2017, : 1601 - 1604
  • [9] Detecting Overlapping Speech with Long Short-Term Memory Recurrent Neural Networks
    Geiger, Juergen T.
    Eyben, Florian
    Schuller, Bjoern
    Rigoll, Gerhard
    [J]. 14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5, 2013, : 1667 - 1671
  • [10] Long Short-Term Memory Recurrent Neural Networks for Antibacterial Peptide Identification
    Youmans, Michael
    Spainhour, Christian
    Qiu, Peng
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM), 2017, : 498 - 502
12345