Training variance and performance evaluation of neural networks in speech

Ewout van den Berg; Bhuvana Ramabhadran; Michael Picheny

ICASSP 2017accepted0 citations

Training variance and performance evaluation of neural networks in speech

Ewout van den Berg, Bhuvana Ramabhadran, Michael Picheny

Abstract

In this work we study variance in the results of neural network training on a wide variety of configurations in automatic speech recognition. Although this variance itself is well known, this is, to the best of our knowledge, the first paper that performs an extensive empirical study on its effects in speech recognition. We view training as sampling from a distribution and show that these distributions can have a substantial variance. These results show the urgent need to rethink the way in which results in the literature are reported and interpreted.

BibTeX

@inproceedings{icassp2017_trainingvariance,
  title = {Training variance and performance evaluation of neural networks in speech},
  author = {Ewout van den Berg and Bhuvana Ramabhadran and Michael Picheny},
  booktitle = {ICASSP 2017},
  year = {2017}
}