Classifying unprompted speech by retraining LSTM nets

Authors:
Nicole Beringer;Alex Graves;Florian Schiel;Jürgen Schmidhuber
Affiliations:
IDSIA, Manno-Lugano, Switzerland;IDSIA, Manno-Lugano, Switzerland;Schiel BAS Services, Munich, Germany;IDSIA, Manno-Lugano, Switzerland
Venue:
ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I
Year:
2005

Citing 3
Cited 0

Neural networks and the bias/variance dilemma

Neural Computation
Long Short-Term Memory

Neural Computation
Bidirectional recurrent neural networks

IEEE Transactions on Signal Processing

Quantified Score

Hi-index	0.00

Visualization

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. By training first on a fraction of the data, then retraining on another fraction, we both reduce time costs and significantly improve recognition rates. For comparison we show recognition rates of Hidden Markov Models (HMMs) on the same corpus, and provide a promising extrapolation for HMM-LSTM hybrids.