Sequence training and adaptation of highway deep neural networks

  • Liang Lu
  • Published 2016 in
    2016 IEEE Spoken Language Technology Workshop…

Abstract

Highway deep neural network (HDNN) is a type of depth-gated feedforward neural network, which has shown to be easier to train with more hidden layers and also generalise better compared to conventional plain deep neural networks (DNNs). Previously, we investigated a structured HDNN architecture for speech recognition, in which the two gate functions were… (More)
DOI: 10.1109/SLT.2016.7846304

Topics

7 Figures and Tables

Cite this paper

@article{Lu2016SequenceTA, title={Sequence training and adaptation of highway deep neural networks}, author={Liang Lu}, journal={2016 IEEE Spoken Language Technology Workshop (SLT)}, year={2016}, pages={461-466} }