Framewise phoneme classification with bidirectional LSTM and other neural network architectures

Alex Graves, Jürgen Schmidhuber

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4265 Scopus citations

Abstract

In this paper, we present bidirectional Long Short Term Memory (LSTM) networks, and a modified, full gradient version of the LSTM learning algorithm. We evaluate Bidirectional LSTM (BLSTM) and several other network architectures on the benchmark task of framewise phoneme classification, using the TIMIT database. Our main findings are that bidirectional networks outperform unidirectional ones, and Long Short Term Memory (LSTM) is much faster and also more accurate than both standard Recurrent Neural Nets (RNNs) and time-windowed Multilayer Perceptrons (MLPs). Our results support the view that contextual information is crucial to speech processing, and suggest that BLSTM is an effective architecture with which to exploit it. © 2005 Elsevier Ltd. All rights reserved.
Original languageEnglish (US)
Title of host publicationNeural Networks
Pages602-610
Number of pages9
DOIs
StatePublished - Jul 1 2005
Externally publishedYes

Bibliographical note

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

ASJC Scopus subject areas

  • Artificial Intelligence
  • Cognitive Neuroscience

Fingerprint

Dive into the research topics of 'Framewise phoneme classification with bidirectional LSTM and other neural network architectures'. Together they form a unique fingerprint.

Cite this