Bidirectional Decoder Networks for Attention-Based End-to-End Offline Handwriting Recognition

By Patrick Doetsch, Albert Zeyer, Hermann Ney. 2016

27 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Hermann Ney
2. Albert Zeyer
3. Tamer Alkhouli
4. Ralf Schlüter
5. Li Deng
6. Jinyu Li
7. Oscar Koller
8. Dong Yu

In Model Architectures

1. Hermann Ney
2. Albert Zeyer
3. Tamer Alkhouli
4. Ralf Schlüter
5. Jinyu Li

Citations in the corpus

• RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech Recognition (2018, background): “…(min WER, max BLEU), • label smoothing, scheduled sampling, • TensorFlow backend and the old Theano backend, which has a separate fast attention implementation (Doetsch et al., 2016), fast CUDA MDLSTM kernels (Voigtlaender et al., 2016), as well as fast sequence training (Zeyer et al., 2017c).”