Word Beam Search: A Connectionist Temporal Classification Decoding Algorithm
Authors:
- Harald ScheidlHSHarald Scheidl
- Stefan FielSFStefan Fiel
- Robert SablatnigRSRobert Sablatnig
- 1 August 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 253-258
Abstract
Recurrent Neural Networks (RNNs) are used for sequence recognition tasks such as Handwritten Text Recognition (HTR) or speech recognition. If trained with the Connectionist Temporal Classification (CTC) loss function, the output of such a RNN is a matrix containing character probabilities for each time-step. A CTC decoding algorithm maps these character probabilities to the final text. Token passing is such an algorithm and is able to constrain the recognized text to a sequence of dictionary words. However, the running time of token passing depends quadratically on the dictionary size and it is not able to decode arbitrary character strings like numbers. This paper proposes word beam search decoding, which is able to tackle these problems. It constrains words to those contained in a dictionary, allows arbitrary non-word character strings between words, optionally integrates a word-level language model and has a better running time than token passing. The proposed algorithm outperforms best path decoding, vanilla beam search decoding and token passing on the IAM and Bentham HTR datasets. An open-source implementation is provided.Keywords
This publication has 9 references indexed in Scilit:
- An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- ICFHR2014 Competition on Handwritten Text Recognition on Transcriptorium Datasets (HTRtS)2014
- Supervised Sequence Labelling with Recurrent Neural Networks2012
- Advanced Data Structures2008
- A Novel Connectionist System for Unconstrained Handwriting RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Connectionist temporal classification2006
- The IAM-database: an English sentence database for offline handwriting recognitionInternational Journal on Document Analysis and Recognition (IJDAR), 2002
- Look-ahead techniques for fast beam searchComputer Speech & Language, 2000
- An efficient implementation of trie structuresSoftware: Practice and Experience, 1992