OPEN VOCABULARY HANDWRITING RECOGNITION USING COMBINED WORD-LEVEL AND CHARACTER-LEVEL LANGUAGE MODELS

被引：0

作者：

Kozielski, Michal ^{[1
]}

Rybach, David ^{[1
]}

Hahn, Stefan ^{[1
]}

Schlueter, Ralf ^{[1
]}

Ney, Hermann ^{[1
]}

机构：

[1] Rhein Westfal TH Aachen, Dept Comp Sci, Aachen, Germany

来源：

2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2013年

关键词：

open vocabulary recognition; handwriting recognition; character-based language models; NORMALIZATION; COMBINATION;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

In this paper, we present a unified search strategy for open vocabulary handwriting recognition using weighted finite state transducers. Additionally to a standard word-level language model we introduce a separate n-gram character-level language model for out-of-vocabulary word detection and recognition. The probabilities assigned by those two models are combined into one Bayes decision rule. We evaluate the proposed method on the IAM database of English handwriting. An improvement from 22.2% word error rate to 1 7.3 % is achieved comparing to the closed-vocabulary scenario and the best published result.

引用

页码：8257 / 8261

页数：5

共 50 条

[41] Affinity Maturation of Homophones in Word-Level Speech Recognition
Ghosh, P.
Chingtham, T. S.
Ghose, M. K.
[J]. RECENT DEVELOPMENTS IN MACHINE LEARNING AND DATA ANALYTICS, 2019, 740 : 137 - 142
[42] Word-level language identification in The Chymistry of Isaac Newton
King, Levi
Kuebler, Sandra
Hooper, Wallace
[J]. DIGITAL SCHOLARSHIP IN THE HUMANITIES, 2015, 30 (04) : 532 - 540
[43] An analytical handwritten word recognition system with word-level discriminant training
Tay, YH
Lallican, PM
Khalid, M
Knerr, S
Viard-Gaudin, C
[J]. SIXTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, PROCEEDINGS, 2001, : 726 - 730
[44] CHARACTER-LEVEL LANGUAGE MODELING WITH HIERARCHICAL RECURRENT NEURAL NETWORKS
Hwang, Kyuyeon
Sung, Wonyong
[J]. 2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, : 5720 - 5724
[45] WORD-LEVEL TONE MODELING FOR MANDARIN SPEECH RECOGNITION
Lei, Xin
Ostendorf, Mari
[J]. 2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL IV, PTS 1-3, 2007, : 665 - +
[46] Full transformer network with masking future for word-level sign language recognition q
Du, Yao
Xie, Pan
Wang, Mingye
Hu, Xiaohui
Zhao, Zheng
Liu, Jiaqi
[J]. NEUROCOMPUTING, 2022, 500 : 115 - 123
[47] Joint Word- and Character-level Embedding CNN-RNN Models for Punctuation Restoration
Tundik, Mate Akos
Szaszak, Gyorgy
[J]. 2018 9TH IEEE INTERNATIONAL CONFERENCE ON COGNITIVE INFOCOMMUNICATIONS (COGINFOCOM), 2018, : 135 - 140
[48] Perception of Word-level Prominence in Free Word Order Language Discourse
Luchkina, Tatiana
Cole, Jennifer S.
[J]. LANGUAGE AND SPEECH, 2021, 64 (02) : 381 - 412
[49] Gating Mechanisms for Combining Character and Word-level Word Representations: An Empirical Study
Balazs, Jorge A.
Matsuo, Yutaka
[J]. NAACL HLT 2019: THE 2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES: PROCEEDINGS OF THE STUDENT RESEARCH WORKSHOP, 2019, : 110 - 124
[50] Character-Level Language Modeling with Deeper Self-Attention
Al-Rfou, Rami
Choe, Dokook
Constant, Noah
Guo, Mandy
Jones, Llion
[J]. THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 3159 - 3166

← 1 2 3 4 5 →