ICDAR 2009 Arabic handwriting recognition competition

V Märgner, H El Abed - 2009 10th International Conference on …, 2009 - ieeexplore.ieee.org
This paper describes the Online Arabic handwritingrecognition competition held at ICDAR
2009. This firstcompetition uses the ADAB-database with Arabic onlinehandwritten words …

Extracting deep neural network bottleneck features using low-rank matrix factorization

Y Zhang, E Chuangsuwanich… - 2014 IEEE international …, 2014 - ieeexplore.ieee.org
In this paper, we investigate the use of deep neural networks (DNNs) to generate a stacked
bottleneck (SBN) feature representation for low-resource speech recognition. We examine …

Hierarchical hybrid MLP/HMM or rather MLP features for a discriminatively trained gaussian HMM: a comparison for offline handwriting recognition

P Dreuw, P Doetsch, C Plahl… - 2011 18th IEEE …, 2011 - ieeexplore.ieee.org
We use neural network based features extracted by a hierarchical multilayer-perceptron
(MLP) network either in a hybrid MLP/HMM approach or to discriminatively retrain a …

The TAO of ATWV: Probing the mysteries of keyword search performance

S Wegmann, A Faria, A Janin… - … IEEE Workshop on …, 2013 - ieeexplore.ieee.org
In this paper we apply diagnostic analysis to gain a deeper understanding of the
performance of the the keyword search system that we have developed for conversational …

Multilingual techniques for low resource automatic speech recognition

E Chuangsuwanich - 2016 - dspace.mit.edu
Out of the approximately 7000 languages spoken around the world, there are only about
100 languages with Automatic Speech Recognition (ASR) capability. This is due to the fact …

ICFHR 2010-Arabic handwriting recognition competition

V Märgner, H El Abed - 2010 12th International Conference on …, 2010 - ieeexplore.ieee.org
This paper describes the Arabic handwriting recognition competition held at International
Conference on Frontiers in Handwriting Recognition (ICFHR 2010) in Kolkata, India. This …

[PDF][PDF] Hierarchical bottle neck features for LVCSR

C Plahl, R Schlüter, H Ney - … annual conference of the international speech …, 2010 - Citeseer
This paper investigates the combination of different neural network topologies for
probabilistic feature extraction. On one hand, a five-layer neural network used in bottle neck …

Cross-lingual portability of Chinese and English neural network features for French and German LVCSR

C Plahl, R Schlüter, H Ney - 2011 IEEE Workshop on Automatic …, 2011 - ieeexplore.ieee.org
This paper investigates neural network (NN) based cross-lingual probabilistic features.
Earlier work reports that intra-lingual features consistently outperform the corresponding …

The rwth large vocabulary arabic handwriting recognition system

M Hamdani, P Doetsch, M Kozielski… - 2014 11th IAPR …, 2014 - ieeexplore.ieee.org
This paper describes the RWTH system for large vocabulary Arabic handwriting recognition.
The recognizer is based on Hidden Markov Models (HMMs) with state of the art methods for …

RWTH OCR: A large vocabulary optical character recognition system for Arabic scripts

P Dreuw, D Rybach, G Heigold, H Ney - Guide to OCR for Arabic scripts, 2012 - Springer
We present a novel large vocabulary OCR system, which implements a confidence-and
margin-based discriminative training approach for model adaptation of an HMM-based …