Semi-Supervised Phoneme Recognition with Recurrent Ladder Networks
Computation and Language
2017-09-20 v2 Machine Learning
Neural and Evolutionary Computing
Abstract
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% of all labels which demonstrates that the model is capable of using unsupervised data as an effective regulariser.
Cite
@article{arxiv.1706.02124,
title = {Semi-Supervised Phoneme Recognition with Recurrent Ladder Networks},
author = {Marian Tietz and Tayfun Alpay and Johannes Twiefel and Stefan Wermter},
journal= {arXiv preprint arXiv:1706.02124},
year = {2017}
}