no code implementations • 2 Jan 2018 • Kanishka Rao, Haşim Sak, Rohit Prabhavalkar
The model consists of an `encoder', which is initialized from a connectionist temporal classification-based (CTC) acoustic model, and a `decoder' which is partially initialized from a recurrent neural network language model trained on text data alone.
no code implementations • 24 Jul 2015 • Haşim Sak, Andrew Senior, Kanishka Rao, Françoise Beaufays
We have recently shown that deep Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) outperform feed forward deep neural networks (DNNs) as acoustic models for speech recognition.
1 code implementation • 5 Feb 2014 • Haşim Sak, Andrew Senior, Françoise Beaufays
However, in contrast to the deep neural networks, the use of RNNs in speech recognition has been limited to phone recognition in small scale tasks.