Rescoring Sequence-to-Sequence Models for Text Line Recognition with CTC-Prefixes
- 18 May 2022
- book chapter
- Published by Springer Nature
- p. 260-274
Abstract
No abstract availableKeywords
All Related Versions
This publication has 11 references indexed in Scilit:
- tfaip - a Generic and Powerful Research Framework for Deep Learning based on TensorflowJournal of Open Source Software, 2021
- ESPnet-SE: End-To-End Speech Enhancement and Separation Toolkit Designed for ASR Integration2021
- Accurate, data-efficient, unconstrained text recognition with convolutional neural networksPattern Recognition, 2020
- Handwritten Optical Character Recognition (OCR): A Comprehensive Systematic Literature Review (SLR)IEEE Access, 2020
- Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition2019
- Data Augmentation for Recognition of Handwritten Words and Lines Using a CNN-LSTM Network2017
- Gated Convolutional Recurrent Neural Networks for Multilingual Handwriting Recognition2017
- Hybrid CTC/Attention Architecture for End-to-End Speech RecognitionIEEE Journal of Selected Topics in Signal Processing, 2017
- Connectionist temporal classification2006
- The IAM-database: an English sentence database for offline handwriting recognitionInternational Journal on Document Analysis and Recognition (IJDAR), 2002