Semi-Supervised Phoneme Recognition with Recurrent Ladder Networks

06/07/2017

∙

by   Marian Tietz, et al.

∙

0

∙

share

Ladder networks are a notable new concept in the field of semi-supervised learning by showing state-of-the-art results in image recognition tasks while being compatible with many existing neural architectures. We present the recurrent ladder network, a novel modification of the ladder network, for semi-supervised learning of recurrent neural networks which we evaluate with a phoneme recognition task on the TIMIT corpus. Our results show that the model is able to consistently outperform the baseline and achieve fully-supervised baseline performance with only 75 model is capable of using unsupervised data as an effective regulariser.