Abstract
In the first part of this paper, a regular recurrent neural network (RNN) is extended to a bidirectional recurrent neural network (BRNN). The BRNN can be trained without the limitation of using input information just up to a preset future frame. This is accomplished by training it simultaneously in positive and negative time direction. Structure and training procedure of the proposed network are explained. In regression and classification experiments on artificial data, the proposed structure gives better results than other approaches. For real data, classification experiments for phonemes from the TIMIT database show the same tendency. In the second part of this paper, it is shown how the proposed bidirectional structure can be easily modified to allow efficient estimation of the conditional posterior probability of complete symbol sequences without making any explicit assumption about the shape of the distribution. For this part, experiments on real data are reported.
Keywords
TIMITRecurrent neural networkComputer scienceArtificial neural networkFrame (networking)Artificial intelligencePattern recognition (psychology)Symbol (formal)AlgorithmMachine learningHidden Markov model
Affiliated Institutions
Related Publications
Global optimization of a neural network-hidden Markov model hybrid
An original method for integrating artificial neural networks (ANN) with hidden Markov models (HMM) is proposed. ANNs are suitable for performing phonetic classification, wherea...
Backpropagation training for multilayer conditional random field based phone recognition
Conditional random fields (CRFs) have recently found increased popularity in automatic speech recognition (ASR) applications. CRFs have previously been shown to be effective com...
Applying Convolutional Neural Networks concepts to hybrid NN-HMM model for speech recognition
Convolutional Neural Networks (CNN) have showed success in achieving translation invariance for many image processing tasks. The success is largely attributed to the use of loca...
An application of recurrent nets to phone probability estimation
This paper presents an application of recurrent networks for phone probability estimation in large vocabulary speech recognition. The need for efficient exploitation of context ...
Generalization of Back propagation to Recurrent and Higher Order Neural Networks
A general method for deriving backpropagation algorithms for networks with recurrent and higher order networks is introduced. The propagation of activation in these networks is ...
Publication Info
- Year
- 1997
- Type
- article
- Volume
- 45
- Issue
- 11
- Pages
- 2673-2681
- Citations
- 9385
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
9385
OpenAlex
Cite This
Mike Schuster,
Kuldip K. Paliwal
(1997).
Bidirectional recurrent neural networks.
IEEE Transactions on Signal Processing
, 45
(11)
, 2673-2681.
https://doi.org/10.1109/78.650093
Identifiers
- DOI
- 10.1109/78.650093