Patrick Doetsch
Patrick Doetsch
RWTH Aachen
Verified email at apptek.com
Title
Cited by
Cited by
Year
Cross-entropy vs. squared error training: a theoretical and experimental comparison.
P Golik, P Doetsch, H Ney
Interspeech 13, 1756-1760, 2013
1732013
Fast and robust training of recurrent neural networks for offline handwriting recognition
P Doetsch, M Kozielski, H Ney
2014 14th International Conference on Frontiers in Handwriting Recognition …, 2014
1312014
A comprehensive study of deep bidirectional LSTM RNNs for acoustic modeling in speech recognition
A Zeyer, P Doetsch, P Voigtlaender, R Schlüter, H Ney
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
1072017
Handwriting recognition with large multidimensional long short-term memory recurrent neural networks
P Voigtlaender, P Doetsch, H Ney
2016 15th International Conference on Frontiers in Handwriting Recognition …, 2016
912016
Improvements in rwth's system for off-line handwriting recognition
P Doetsch, H Ney
2013 12th International Conference on Document Analysis and Recognition, 935-939, 2013
732013
RETURNN: The RWTH extensible training framework for universal recurrent neural networks
P Doetsch, A Zeyer, P Voigtlaender, I Kulikov, R Schlüter, H Ney
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
512017
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, H Ney
2011 18th IEEE International Conference on Image Processing, 3541-3544, 2011
462011
On the benefits of convolutional neural network combinations in offline handwriting recognition
D Suryani, P Doetsch, H Ney
2016 15th International Conference on Frontiers in Handwriting Recognition …, 2016
322016
Logistic model trees with auc split criterion for the kdd cup 2009 small challenge
P Doetsch, C Buck, P Golik, N Hoppe, M Kramp, J Laudenberg, ...
KDD-Cup 2009 Competition, 77-88, 2009
292009
Sequence-discriminative training of recurrent neural networks
P Voigtlaender, P Doetsch, S Wiesler, R Schlüter, H Ney
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
252015
The rwth large vocabulary arabic handwriting recognition system
M Hamdani, P Doetsch, M Kozielski, AED Mousa, H Ney
2014 11th IAPR International Workshop on Document Analysis Systems, 111-115, 2014
242014
Towards unsupervised learning for handwriting recognition
M Kozielski, M Nuhn, P Doetsch, H Ney
2014 14th International Conference on Frontiers in Handwriting Recognition …, 2014
142014
Comparison of Bernoulli and Gaussian HMMs using a vertical repositioning technique for off-line handwriting recognition
P Doetsch, M Hamdani, H Ney, A Giménez, J Andres-Ferrer, A Juan
2012 International Conference on Frontiers in Handwriting Recognition, 3-7, 2012
132012
Bidirectional decoder networks for attention-based end-to-end offline handwriting recognition
P Doetsch, A Zeyer, H Ney
2016 15th International Conference on Frontiers in Handwriting Recognition …, 2016
122016
Open-lexicon language modeling combining word and character levels
M Kozielski, M Matysiak, P Doetsch, R Schlöter, H Ney
2014 14th International Conference on Frontiers in Handwriting Recognition …, 2014
122014
Improvement of context dependent modeling for Arabic handwriting recognition
M Hamdani, P Doetsch, H Ney
2014 14th International Conference on Frontiers in Handwriting Recognition …, 2014
112014
Multilingual off-line handwriting recognition in real-world images
M Kozielski, P Doetsch, M Hamdani, H Ney
2014 11th IAPR International Workshop on Document Analysis Systems, 121-125, 2014
102014
Segmental Encoder-Decoder Models for Large Vocabulary Automatic Speech Recognition.
E Beck, M Hannemann, P Doetsch, R Schlüter, H Ney
Interspeech, 766-770, 2018
72018
A comprehensive study of batch construction strategies for recurrent neural networks in mxnet
P Doetsch, P Golik, H Ney
arXiv preprint arXiv:1705.02414, 2017
62017
Cross-entropy vs
P Golik, P Doetsch, H Ney
Squared Error Training: a Theoretical and Experimental Comparison, 2013
62013
The system can't perform the operation now. Try again later.
Articles 1–20