Mike Schuster, Kuldip K. Paliwal
Bidirectional recurrent neural networks
Abstract:In the first part of this report (appeared as a full paper as [16]), 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 report, 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.