English

Feature Learning in Deep Neural Networks - Studies on Speech Recognition Tasks

Machine Learning 2018-12-06 v3 Computation and Language Neural and Evolutionary Computing Audio and Speech Processing

Abstract

Recent studies have shown that deep neural networks (DNNs) perform significantly better than shallow networks and Gaussian mixture models (GMMs) on large vocabulary speech recognition tasks. In this paper, we argue that the improved accuracy achieved by the DNNs is the result of their ability to extract discriminative internal representations that are robust to the many sources of variability in speech signals. We show that these representations become increasingly insensitive to small perturbations in the input with increasing network depth, which leads to better speech recognition performance with deeper networks. We also show that DNNs cannot extrapolate to test samples that are substantially different from the training examples. If the training data are sufficiently representative, however, internal features learned by the DNN are relatively stable with respect to speaker differences, bandwidth differences, and environment distortion. This enables DNN-based recognizers to perform as well or better than state-of-the-art systems based on GMMs or shallow networks without the need for explicit model adaptation or feature normalization.

Keywords

Cite

@article{arxiv.1301.3605,
  title  = {Feature Learning in Deep Neural Networks - Studies on Speech Recognition Tasks},
  author = {Dong Yu and Michael L. Seltzer and Jinyu Li and Jui-Ting Huang and Frank Seide},
  journal= {arXiv preprint arXiv:1301.3605},
  year   = {2018}
}

Comments

ICLR 2013, 9 pages, 4 figures

R2 v1 2026-06-21T23:10:12.507Z