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 language | English (US) |
---|---|
Title of host publication | Neural Networks |
Pages | 602-610 |
Number of pages | 9 |
DOIs | |
State | Published - Jul 1 2005 |
Externally published | Yes |
Bibliographical note
Generated from Scopus record by KAUST IRTS on 2022-09-14ASJC Scopus subject areas
- Artificial Intelligence
- Cognitive Neuroscience