Rectifier Nonlinearities Improve Neural Network Acoustic Models

@inproceedings{Maas2013RectifierNI,
  title={Rectifier Nonlinearities Improve Neural Network Acoustic Models},
  author={Andrew L. Maas},
  year={2013}
}
Deep neural network acoustic models produce substantial gains in large vocabulary continuous speech recognition systems. Emerging work with rectified linear (ReL) hidden units demonstrates additional gains in final system performance relative to more commonly used sigmoidal nonlinearities. In this work, we explore the use of deep rectifier networks as acoustic models for the 300 hour Switchboard conversational speech recognition task. Using simple training procedures without pretraining… CONTINUE READING
Highly Influential
This paper has highly influenced 132 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 1,563 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 968 citations

1,564 Citations

0200400600'14'16'18
Citations per Year
Semantic Scholar estimates that this publication has 1,564 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 14 references