Publication
ICASSP 2014
Conference paper

Joint training of convolutional and non-convolutional neural networks

View publication

Abstract

We describe a simple modification of neural networks which consists in extending the commonly used linear layer structure to an arbitrary graph structure. This allows us to combine the benefits of convolutional neural networks with the benefits of regular networks. The joint model has only a small increase in parameter size and training and decoding time are virtually unaffected. We report significant improvements over very strong baselines on two LVCSR tasks and one speech activity detection task. © 2014 IEEE.

Date

Publication

ICASSP 2014

Authors

Share