Sciweavers

2 search results - page 1 / 1
» Classifying Unprompted Speech by Retraining LSTM Nets
Sort
View
190
Voted
ICANN
2005
Springer
16 years 28 days ago
Classifying Unprompted Speech by Retraining LSTM Nets
Abstract. We apply Long Short-Term Memory (LSTM) recurrent neural networks to a large corpus of unprompted speech- the German part of the VERBMOBIL corpus. Training first on a fra...
Nicole Beringer, Alex Graves, Florian Schiel, J&uu...
NCI
2004
132views Neural Networks» more  NCI 2004»
15 years 8 months ago
A comparison between spiking and differentiable recurrent neural networks on spoken digit recognition
In this paper we demonstrate that Long Short-Term Memory (LSTM) is a differentiable recurrent neural net (RNN) capable of robustly categorizing timewarped speech data. We measure ...
Alex Graves, Nicole Beringer, Jürgen Schmidhu...