Semi-Supervised Phoneme Recognition with Recurrent Ladder Networks
arXiv:1706.02124 · doi:10.1007/978-3-319-68600-4_1
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.
References in corpus (5)
- Adam: A Method for Stochastic Optimization
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Semi-Supervised Learning with Ladder Networks
- Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classification
- Semi-supervised Learning with Sparse Autoencoders in Phone Classification