Biologically plausible speech recognition with LSTM neural nets (2004) [5 citations — 1 self]

Download:

by Alex Graves, Douglas Eck, Nicole Beringer, Juergen Schmidhuber

in Proc. of Bio-ADIT

ftp://ftp.idsia.ch/pub/juergen/bioadit2004.pdf

Add To MetaCart

Popular Tags

No tags have been applied to this document.

BibTeX | Add To MetaCart

@INPROCEEDINGS{Graves04biologicallyplausible,
    author = {Alex Graves and Douglas Eck and Nicole Beringer and Juergen Schmidhuber},
    title = {Biologically plausible speech recognition with LSTM neural nets},
    booktitle = {in Proc. of Bio-ADIT},
    year = {2004},
    pages = {127--136}
}

Abstract:

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 netbased approach to speech recognition. 1

Citations

3318	Neural Networks for Pattern Recognition – Bishop - 1995
2335	A tutorial on hidden markov models and selected applications in speech recognition – Rabiner - 1989
344	Connectionist Speech Recognition: A Hybrid Approach – Bourlard, Morgan - 1994
160	An application of recurrent nets to phone probability estimation – Robinson - 1994
137	Long short-term memory – Hochreiter, Schmidhuber - 1997
87	Gradient-based learning algorithms for recurrent networks and their computational complexity – Williams, Zipser - 1995
84	The utility driven dynamic error propagation network – Robinson, Fallside - 1987
81	Generalization of backpropagation with application to a recurrent gas market model – Werbos - 1988
72	Experiments on learning by back propagation – Plaut, Nowlan, et al. - 1986
51	LSTM recurrent networks learn simple context free and context sensitive languages – Gers, Schmidhuber - 2001
25	Making working memory work: A computational model of learning in the prefrontal cortex and basal ganglia – O’Reilly, Frank - 2006
22	Gradient flow in recurrent nets: the difficulty of learning long-term dependencies – Hochreiter, Bengio, et al. - 2001
17	Finding temporal structure in music: Blues improvisation with LSTM recurrent networks – Eck, Schmidhuber - 2002
6	Long Short-Term Memory in Recurrent Neural Networks – Gers - 2001
2	Robust low perplexity voice interfaces – Zheng, Picone - 2001

View or Download | Add to My Collection | Correct Errors