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

@inproceedings{Yu2013FeatureLI,
  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},
  year={2013}
}
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… CONTINUE READING
Highly Influential
This paper has highly influenced 13 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 151 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 3 times over the past 90 days. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-10 of 108 extracted citations

151 Citations

02040'13'14'15'16'17'18
Citations per Year
Semantic Scholar estimates that this publication has 151 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 23 references

Vocal tract length normalization for lvcsr

  • P. Zhan
  • Tech. Rep. CMU-LTI-97-150, Carnegie Mellon Univ…
  • 1997
Highly Influential
13 Excerpts

Switchboard-1 Release 2, Linguistic Data

  • J. Godfrey, E. Holliman
  • 1997
Highly Influential
3 Excerpts

Similar Papers

Loading similar papers…