2005 BidirectionalLSTMNetworksforImp

• (Graves, Fernandez & Shmidhuber, 2005) ⇒ Alex Graves, Santiago Fernandez, and Jurgen Schmidhuber. (2005). “Bidirectional LSTM Networks for Improved Phoneme Classification and Recognition.” In: Artificial Neural Networks: Formal Models and Their Applications -- ICANN 2005. ISBN:978-3-540-28755-1 doi:10.1007/11550907_126

Subject Headings:

Cited By

• http://scholar.google.com/scholar?q=%222005%22+Bidirectional+LSTM+Networks+for+Improved+Phoneme+Classification+and+Recognition

Quotes

Author Keywords

• Speech Recognition; Recurrent Neural Network; Phoneme Classification; Phoneme Recognition; Frame Delay

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 LSTM outperforms both unidirectional LSTM and 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.

References

;

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2005 BidirectionalLSTMNetworksforImp	Jürgen Schmidhuber Alex Graves Santiago Fernandez			Bidirectional LSTM Networks for Improved Phoneme Classification and Recognition				10.1007/11550907_126		2005