Abstract
Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) are local in space and time and closely related to a biological model of memory in the prefrontal cortex. Not only are they more biologically plausible than previous artificial RNNs, they also outperformed them on many artificially generated sequential processing tasks. This encouraged us to apply LSTM to more realistic problems, such as the recognition of spoken digits. Without any modification of the underlying algorithm, we achieved results comparable to state-of-the-art Hidden Markov Model (HMM) based recognisers on both the TIDIGITS and TI46 speech corpora. We conclude that LSTM should be further investigated as a biologically plausible basis for a bottom-up, neural net-based approach to speech recognition.
Keywords
- Hide Markov Model
- Speech Recognition
- Recurrent Neural Network
- Memory Block
- Input Gate
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, access via your institution.
Buying options
Preview
Unable to display preview. Download preview PDF.
References
Williams, R.J., Zipser, D.: Gradient-based learning algorithms for recurrent networks and their computational complexity. In: Chauvin, Y., Rumelhart, D.E. (eds.) Back-propagation: Theory, Architectures and Applications, pp. 433–486. Lawrence Erlbaum Publishers, Hillsdale (1995)
Werbos, P.J.: Generalization of backpropagation with application to a recurrent gas market model. Neural Networks 1 (1988)
Robinson, A.J., Fallside, F.: The utility driven dynamic error propagation network. Technical Report CUED/F-INFENG/TR.1, Cambridge University Engineering Department (1987)
Hochreiter, S., Bengio, Y., Frasconi, P., Schmidhuber, J.: Gradient flow in recurrent nets: the difficulty of learning long-term dependencies. In: Kremer, S.C., Kolen, J.F. (eds.) A Field Guide to Dynamical Recurrent Neural Networks, IEEE Press, Los Alamitos (2001)
Rabiner, L.R.: A tutorial on hidden markov models and selected applications in speech recognition. Proc. IEEE 77, 257–286 (1989)
Bourlard, H., Morgan, N.: Connnectionist Speech Recognition: A Hybrid Approach. Kluwer Academic Publishers, Dordrecht (1994)
Robinson, A.J.: An application of recurrent nets to phone probability estimation. IEEE Transactions on Neural Networks 5, 298–305 (1994)
Hochreiter, S., Schmidhuber, J.: Long Short-Term Memory. Neural Computation 9, 1735–1780 (1997)
Gers, F.: Long Short-Term Memory in Recurrent Neural Networks. PhD thesis (2001)
O’Reilly, R.: Making working memory work: A computational model of learning in the prefrontal cortex and basal ganglia. Technical Report ICS-03-03, ICS (2003)
Gers, F.A., Schmidhuber, J.: LSTM recurrent networks learn simple context free and context sensitive languages. IEEE Transactions on Neural Networks 12, 1333–1340 (2001)
Eck, D., Schmidhuber, J.: Finding temporal structure in music: Blues improvisation with LSTM recurrent networks. In: Bourlard, H. (ed.) Proceedings of the 2002 IEEE Workshop in Neural Networks for Signal Processing XII, pp. 747–756. IEEE, New York (2002)
Young, S.: The HTK Book. Cambridge University Press, Cambridge (1995/1996)
Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, Inc., Oxford (1995)
Plaut, D.C., Nowlan, S.J., Hinton, G.E.: Experiments on learning back propagation. Technical Report CMU–CS–86–126, Carnegie–Mellon University, Pittsburgh, PA (1986)
Zheng, F., Picone, J.: Robust low perplexity voice interfaces. Technical report, MITRE Corporation (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Graves, A., Eck, D., Beringer, N., Schmidhuber, J. (2004). Biologically Plausible Speech Recognition with LSTM Neural Nets. In: Ijspeert, A.J., Murata, M., Wakamiya, N. (eds) Biologically Inspired Approaches to Advanced Information Technology. BioADIT 2004. Lecture Notes in Computer Science, vol 3141. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-27835-1_10
Download citation
DOI: https://doi.org/10.1007/978-3-540-27835-1_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23339-8
Online ISBN: 978-3-540-27835-1
eBook Packages: Springer Book Archive