Patrick Doetsch

Publication Activity (10 Years)

Years Active: 2009-2018
Publications (10 Years): 15

Top Topics

Handwritten Text

Handwriting Recognition

Top Venues

Publications

Eugen Beck, Albert Zeyer, Patrick Doetsch, André Merboldt, Ralf Schlüter, Hermann Ney
Sequence Modeling and Alignment for LVCSR-Systems. ITG Symposium on Speech Communication (2018)
Javier Jorge, Adria A. Martinez-Villaronga, Pavel Golik, Adrià Giménez, Joan Albert Silvestre-Cerdà, Patrick Doetsch, Vicent Andreu Císcar, Hermann Ney, Alfons Juan, Albert Sanchís
MLLP-UPV and RWTH Aachen Spanish ASR Systems for the IberSpeech-RTVE 2018 Speech-to-Text Transcription Challenge. IberSPEECH (2018)
Patrick Doetsch, Mirko Hannemann, Ralf Schlüter, Hermann Ney
Inverted Alignments for End-to-End Automatic Speech Recognition. IEEE J. Sel. Top. Signal Process. 11 (8) (2017)
Albert Zeyer, Patrick Doetsch, Paul Voigtlaender, Ralf Schlüter, Hermann Ney
A comprehensive study of deep bidirectional LSTM RNNS for acoustic modeling in speech recognition. ICASSP (2017)
Patrick Doetsch, Pavel Golik, Hermann Ney
A comprehensive study of batch construction strategies for recurrent neural networks in MXNet. CoRR (2017)
Patrick Doetsch, Albert Zeyer, Paul Voigtlaender, Ilia Kulikov, Ralf Schlüter, Hermann Ney
Returnn: The RWTH extensible training framework for universal recurrent neural networks. ICASSP (2017)
Patrick Doetsch, Albert Zeyer, Hermann Ney
Bidirectional Decoder Networks for Attention-Based End-to-End Offline Handwriting Recognition. ICFHR (2016)
Albert Zeyer, Patrick Doetsch, Paul Voigtlaender, Ralf Schlüter, Hermann Ney
A Comprehensive Study of Deep Bidirectional LSTM RNNs for Acoustic Modeling in Speech Recognition. CoRR (2016)
Patrick Doetsch, Albert Zeyer, Paul Voigtlaender, Ilya Kulikov, Ralf Schlüter, Hermann Ney
RETURNN: The RWTH Extensible Training framework for Universal Recurrent Neural Networks. CoRR (2016)
Ralf Schlüter, Patrick Doetsch, Pavel Golik, Markus Kitza, Tobias Menne, Kazuki Irie, Zoltán Tüske, Albert Zeyer
Automatic Speech Recognition Based on Neural Networks. SPECOM (2016)
Paul Voigtlaender, Patrick Doetsch, Hermann Ney
Handwriting Recognition with Large Multidimensional Long Short-Term Memory Recurrent Neural Networks. ICFHR (2016)
Dewi Suryani, Patrick Doetsch, Hermann Ney
On the Benefits of Convolutional Neural Network Combinations in Offline Handwriting Recognition. ICFHR (2016)
Mahdi Hamdani, Patrick Doetsch, Hermann Ney
Bagging by design for continuous Handwriting Recognition using multi-objective particle swarm optimization. ICDAR (2015)
Mahdi Hamdani, M. Ali Basha Shaik, Patrick Doetsch, Hermann Ney
Investigation of Segmental Conditional Random Fields for large vocabulary handwriting recognition. ICDAR (2015)
Paul Voigtlaender, Patrick Doetsch, Simon Wiesler, Ralf Schlüter, Hermann Ney
Sequence-discriminative training of recurrent neural networks. ICASSP (2015)
Michal Kozielski, Malte Nuhn, Patrick Doetsch, Hermann Ney
Towards Unsupervised Learning for Handwriting Recognition. ICFHR (2014)
Mahdi Hamdani, Patrick Doetsch, Michal Kozielski, Amr El-Desoky Mousa, Hermann Ney
The RWTH Large Vocabulary Arabic Handwriting Recognition System. Document Analysis Systems (2014)
Patrick Doetsch, Michal Kozielski, Hermann Ney
Fast and Robust Training of Recurrent Neural Networks for Offline Handwriting Recognition. ICFHR (2014)
Mahdi Hamdani, Patrick Doetsch, Hermann Ney
Improvement of Context Dependent Modeling for Arabic Handwriting Recognition. ICFHR (2014)
Michal Kozielski, Patrick Doetsch, Mahdi Hamdani, Hermann Ney
Multilingual Off-Line Handwriting Recognition in Real-World Images. Document Analysis Systems (2014)
Michal Kozielski, Martin Matysiak, Patrick Doetsch, Ralf Schlüter, Hermann Ney
Open-Lexicon Language Modeling Combining Word and Character Levels. ICFHR (2014)
Michal Kozielski, Patrick Doetsch, Hermann Ney
Improvements in RWTH's System for Off-Line Handwriting Recognition. ICDAR (2013)
Pavel Golik, Patrick Doetsch, Hermann Ney
Cross-entropy vs. squared error training: a theoretical and experimental comparison. INTERSPEECH (2013)
Patrick Doetsch, Mahdi Hamdani, Hermann Ney, Adrià Giménez, Jesús Andrés-Ferrer, Alfons Juan
Comparison of Bernoulli and Gaussian HMMs Using a Vertical Repositioning Technique for Off-Line Handwriting Recognition. ICFHR (2012)
Philippe Dreuw, Patrick Doetsch, Christian Plahl, Hermann Ney
Hierarchical hybrid MLP/HMM or rather MLP features for a discriminatively trained Gaussian HMM: A comparison for offline handwriting recognition. ICIP (2011)
Patrick Doetsch, Christian Buck, Pavlo Golik, Niklas Hoppe, Michael Kramp, Johannes Laudenberg, Christian Oberdörfer, Pascal Steingrube, Jens Forster, Arne Mauser
Logistic Model Trees with AUC Split Criterion for the KDD Cup 2009 Small Challenge. KDD Cup (2009)