Constructing Long Short-Term Memory based Deep Recurrent Neural Networks for Large Vocabulary Speech Recognition
Abstract
Long short-term memory (LSTM) based acoustic modeling methods have recently been shown to give state-of-the-art performance on some speech recognition tasks. To achieve a further performance improvement, in this research, deep extensions on LSTM are investigated considering that deep hierarchical model has turned out to be more efficient than a shallow one. Motivated by previous research on constructing deep recurrent neural networks (RNNs), alternative deep LSTM architectures are proposed and empirically evaluated on a large vocabulary conversational telephone speech recognition task. Meanwhile, regarding to multi-GPU devices, the training process for LSTM networks is introduced and discussed. Experimental results demonstrate that the deep LSTM networks benefit from the depth and yield the state-of-the-art performance on this task.
Cite
@article{arxiv.1410.4281,
title = {Constructing Long Short-Term Memory based Deep Recurrent Neural Networks for Large Vocabulary Speech Recognition},
author = {Xiangang Li and Xihong Wu},
journal= {arXiv preprint arXiv:1410.4281},
year = {2015}
}
Comments
submitted to ICASSP 2015 which does not perform blind reviews