2005 Special Issue: Framewise phoneme classification with bidirectional LSTM and other neural network architectures
2005 Special Issue: Framewise phoneme classification with bidirectional LSTM and other neural network architectures
Alex Graves,J. Schmidhuber
2005 · DOI: 10.1016/J.NEUNET.2005.06.042
4,790 Citations
TLDR
The main findings are that bidirectional networks outperform unidirectional ones, and Long Short Term Memory (LSTM) is much faster and also more accurate than both standard Recurrent Neural Nets (RNNs) and time-windowed Multilayer Perceptrons (MLPs).