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 proceedingConference contribution

11 Scopus citations

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 languageEnglish (US)
Title of host publicationProceedings of the IASTED International Conference on Neural Networks and Computational Intelligence
Pages164-168
Number of pages5
StatePublished - Dec 1 2004
Externally publishedYes

Bibliographical note

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

Fingerprint

Dive into the research topics of 'A comparison between spiking and differentiable recurrent neural networks on spoken digit recognition'. Together they form a unique fingerprint.

Cite this