Feature Learning with Gaussian Restricted Boltzmann Machine for Robust Speech Recognition
Computation and Language
2013-09-25 v1 Machine Learning
Sound
Abstract
In this paper, we first present a new variant of Gaussian restricted Boltzmann machine (GRBM) called multivariate Gaussian restricted Boltzmann machine (MGRBM), with its definition and learning algorithm. Then we propose using a learned GRBM or MGRBM to extract better features for robust speech recognition. Our experiments on Aurora2 show that both GRBM-extracted and MGRBM-extracted feature performs much better than Mel-frequency cepstral coefficient (MFCC) with either HMM-GMM or hybrid HMM-deep neural network (DNN) acoustic model, and MGRBM-extracted feature is slightly better.
Keywords
Cite
@article{arxiv.1309.6176,
title = {Feature Learning with Gaussian Restricted Boltzmann Machine for Robust Speech Recognition},
author = {Xin Zheng and Zhiyong Wu and Helen Meng and Weifeng Li and Lianhong Cai},
journal= {arXiv preprint arXiv:1309.6176},
year = {2013}
}
Comments
4 pages, 2 figures