2005 FramewisePhonemeClassificationw

• (Graves & Schmidhuber, 2005) ⇒ Alex Graves, and Jürgen Schmidhuber. (2005). “Framewise Phoneme Classification with Bidirectional LSTM and Other Neural Network Architectures.” In: Neural Networks Journal, 18(5-6). doi:10.1016/j.neunet.2005.06.042

Subject Headings: Bidirectional LSTM.

Cited By

• http://scholar.google.com/scholar?q=%222005%22+Framewise+Phoneme+Classification+with+Bidirectional+LSTM+and+Other+Neural+Network+Architectures
• http://dl.acm.org/citation.cfm?id=1120509.1120527&preflayout=flat#citedby

Quotes

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.

References

;

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2005 FramewisePhonemeClassificationw	Jürgen Schmidhuber Alex Graves			Framewise Phoneme Classification with Bidirectional LSTM and Other Neural Network Architectures				10.1016/j.neunet.2005.06.042		2005