Bidirectional LSTM networks for improved phoneme classification and recognition

Authors:
Alex Graves;Santiago Fernández;Jürgen Schmidhuber
Affiliations:
IDSIA, Manno-Lugano, Switzerland;IDSIA, Manno-Lugano, Switzerland;TU Munich, Munich, Germany
Venue:
ICANN'05 Proceedings of the 15th international conference on Artificial neural networks: formal models and their applications - Volume Part II
Year:
2005

Citing 5
Cited 8

Connectionist Speech Recognition: A Hybrid Approach

Connectionist Speech Recognition: A Hybrid Approach
Learning precise timing with lstm recurrent networks

The Journal of Machine Learning Research
2005 Special Issue: Framewise phoneme classification with bidirectional LSTM and other neural network architectures

Neural Networks - 2005 Special issue: IJCNN 2005
Long Short-Term Memory

Neural Computation
Bidirectional recurrent neural networks

IEEE Transactions on Signal Processing

Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks

ICML '06 Proceedings of the 23rd international conference on Machine learning
Sequence labelling in structured domains with hierarchical recurrent neural networks

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
An application of recurrent neural networks to discriminative keyword spotting

ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Hybrid HMM/BLSTM-RNN for robust speech recognition

TSD'10 Proceedings of the 13th international conference on Text, speech and dialogue
Tandem decoding of children's speech for keyword detection in a child-robot interaction scenario

ACM Transactions on Speech and Language Processing (TSLP)
A multitask approach to continuous five-dimensional affect sensing in natural speech

ACM Transactions on Interactive Intelligent Systems (TiiS) - Special Issue on Affective Interaction in Natural Environments
Improving keyword spotting with a tandem BLSTM-DBN architecture

NOLISP'09 Proceedings of the 2009 international conference on Advances in Nonlinear Speech Processing
Combining speech attribute detection and penalized logistic regression for phoneme recognition

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we carry out two experiments on the TIMIT speech corpus with bidirectional and unidirectional Long Short Term Memory (LSTM) networks. In the first experiment (framewise phoneme classification) we find that bidirectional LSTMoutperforms both unidirectional LSTMand conventional Recurrent Neural Networks (RNNs). In the second (phoneme recognition) we find that a hybrid BLSTM-HMM system improves on an equivalent traditional HMM system, as well as unidirectional LSTM-HMM.