Framewise phoneme classification with bidirectional LSTM networks

• Published in: Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005 Vol. 4; pp. 2047 - 2052 vol. 4
• Main Authors: Graves, A., Schmidhuber, J.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 2005
• Subjects: Acoustic measurements; Data analysis; Electronic mail; Error correction; Hidden Markov models; Memory architecture; Neural networks; Recurrent neural networks; Speech recognition

In this paper, we apply bidirectional training to a long short term memory (LSTM) network for the first time. We also present a modified, full gradient version of the LSTM learning algorithm. We discuss the significance of framewise phoneme classification to continuous speech recognition, and the va...