tlooto
Sign up
Computer ScienceMedicine

Framewise phoneme classification with bidirectional LSTM and other neural network architectures

Alex Graves, J. Schmidhuber

2005.6.1NEURAL NETWORKS

DOI: 10.1016/j.neunet.2005.06.042

tlooto Summary

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).

Abstract

Abstract is not available.

Citation format

GRAVES, Alex; SCHMIDHUBER, J. Framewise phoneme classification with bidirectional LSTM and other neural network architectures. NEURAL NETWORKS, 2005, 18 5-6: 602–10.