173 citations · 178 across the 3 of their papers we have counts for
3 papers
A comprehensive study of batch construction strategies for recurrent neural networks in MXNet
Patrick Doetsch, Pavel Golik, Hermann Ney
In this work we compare different batch construction methods for mini-batch training of recurrent neural networks. While popular implementations like TensorFlow and MXNet suggest a…
RETURNN: The RWTH Extensible Training framework for Universal Recurrent Neural Networks
Patrick Doetsch, Albert Zeyer, Paul Voigtlaender +3
In this work we release our extensible and easily configurable neural network training software. It provides a rich set of functional layers with a particular focus on efficient tr…
A Comprehensive Study of Deep Bidirectional LSTM RNNs for Acoustic Modeling in Speech Recognition
Albert Zeyer, Patrick Doetsch, Paul Voigtlaender +2
We present a comprehensive study of deep bidirectional long short-term memory (LSTM) recurrent neural network (RNN) based acoustic models for automatic speech recognition (ASR). We…