ICDAR 2009 Arabic handwriting recognition competition
This paper describes the Online Arabic handwritingrecognition competition held at ICDAR
2009. This firstcompetition uses the ADAB-database with Arabic onlinehandwritten words …
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 …
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
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 …
(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
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 …
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 …
100 languages with Automatic Speech Recognition (ASR) capability. This is due to the fact …
ICFHR 2010-Arabic handwriting recognition competition
This paper describes the Arabic handwriting recognition competition held at International
Conference on Frontiers in Handwriting Recognition (ICFHR 2010) in Kolkata, India. This …
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 …
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 …
Earlier work reports that intra-lingual features consistently outperform the corresponding …
The rwth large vocabulary arabic handwriting recognition system
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 …
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
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 …
margin-based discriminative training approach for model adaptation of an HMM-based …