3 accepted papers
Recent experiments show that deep bidirectional long short-term memory (BLSTM) recurrent neural network acoustic models outperform feedforward neural networks for automatic speech recognition (ASR). However, their training requires a lot of tuning and experience. In this work, we provide a comprehen…
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 training of recurrent neural network topologies on multiple GPUs. The source of the software package is public and freely…
We investigate sequence-discriminative training of long shortterm memory recurrent neural networks using the maximum mutual information criterion. We show that although recurrent neural networks already make use of the whole observation sequence and are able to incorporate more contextual informatio…