• DOI:10.1186/S13636-015-0068-3
Corpus ID: 217950236

Phone recognition with hierarchical convolutional deep maxout networks

@article{Tth2015PhoneRW,
  title={Phone recognition with hierarchical convolutional deep maxout networks},
  author={L. T{\'o}th},
  journal={EURASIP Journal on Audio, Speech, and Music Processing},
  year={2015},
  volume={2015},
  pages={1-13}
}

L. Tóth

Published 2015

Computer Science

EURASIP Journal on Audio, Speech, and Music Processing

Deep convolutional neural networks (CNNs) have recently been shown to outperform fully connected deep neural networks (DNNs) both on low-resource and on large-scale speech tasks. Experiments indicate that convolutional networks can attain a 10–15 % relative improvement in the word error rate of large vocabulary recognition tasks over fully connected deep networks. Here, we explore some refinements to CNNs that have not been pursued by other authors. First, the CNN papers published up till now… CONTINUE READING

View on Springer

asmp-eurasipjournals.springeropen.com

Save to Library

Create Alert

Cite

Launch Research Feed