A comparison between spiking and differentiable recurrent neural networks on spoken digit recognition

Alex Graves; Nicole Beringer; Jürgen Schmidhuber

A comparison between spiking and differentiable recurrent neural networks on spoken digit recognition

Alex Graves, Nicole Beringer, Jürgen Schmidhuber

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper we demonstrate that Long Short-Term Memory (LSTM) is a differentiable recurrent neural net (RNN) capable of robustly categorizing time-warped speech data. We measure its performance on a spoken digit identification task, where the data was spike-encoded in such a way that classifying the utterances became a difficult challenge in non-linear time-warping. We find that LSTM gives greatly superior results to an SNN found in the literature, and conclude that the architecture has a place in domains that require the learning of large timewarped datasets, such as automatic speech recognition.

Original language	English (US)
Title of host publication	Proceedings of the IASTED International Conference on Neural Networks and Computational Intelligence
Pages	164-168
Number of pages	5
State	Published - Dec 1 2004
Externally published	Yes

Cite this

@inproceedings{601bdad5eb2d47b4aeb2722b137d35f0,

title = "A comparison between spiking and differentiable recurrent neural networks on spoken digit recognition",

abstract = "In this paper we demonstrate that Long Short-Term Memory (LSTM) is a differentiable recurrent neural net (RNN) capable of robustly categorizing time-warped speech data. We measure its performance on a spoken digit identification task, where the data was spike-encoded in such a way that classifying the utterances became a difficult challenge in non-linear time-warping. We find that LSTM gives greatly superior results to an SNN found in the literature, and conclude that the architecture has a place in domains that require the learning of large timewarped datasets, such as automatic speech recognition.",

author = "Alex Graves and Nicole Beringer and J{\"u}rgen Schmidhuber",

note = "Generated from Scopus record by KAUST IRTS on 2022-09-14",

year = "2004",

month = dec,

day = "1",

language = "English (US)",

pages = "164--168",

booktitle = "Proceedings of the IASTED International Conference on Neural Networks and Computational Intelligence",

}

TY - GEN

T1 - A comparison between spiking and differentiable recurrent neural networks on spoken digit recognition

AU - Graves, Alex

AU - Beringer, Nicole

AU - Schmidhuber, Jürgen

N1 - Generated from Scopus record by KAUST IRTS on 2022-09-14

PY - 2004/12/1

Y1 - 2004/12/1

N2 - In this paper we demonstrate that Long Short-Term Memory (LSTM) is a differentiable recurrent neural net (RNN) capable of robustly categorizing time-warped speech data. We measure its performance on a spoken digit identification task, where the data was spike-encoded in such a way that classifying the utterances became a difficult challenge in non-linear time-warping. We find that LSTM gives greatly superior results to an SNN found in the literature, and conclude that the architecture has a place in domains that require the learning of large timewarped datasets, such as automatic speech recognition.

AB - In this paper we demonstrate that Long Short-Term Memory (LSTM) is a differentiable recurrent neural net (RNN) capable of robustly categorizing time-warped speech data. We measure its performance on a spoken digit identification task, where the data was spike-encoded in such a way that classifying the utterances became a difficult challenge in non-linear time-warping. We find that LSTM gives greatly superior results to an SNN found in the literature, and conclude that the architecture has a place in domains that require the learning of large timewarped datasets, such as automatic speech recognition.

UR - http://www.scopus.com/inward/record.url?scp=11144352118&partnerID=8YFLogxK

M3 - Conference contribution

SP - 164

EP - 168

BT - Proceedings of the IASTED International Conference on Neural Networks and Computational Intelligence

ER -

A comparison between spiking and differentiable recurrent neural networks on spoken digit recognition

Abstract

Other files and links

Fingerprint

Cite this