Semi-Supervised Phoneme Recognition with Recurrent Ladder Networks
This addresses the problem of reducing labeled data needs for phoneme recognition, but it is incremental as it adapts an existing method to a new architecture.
The paper tackled semi-supervised phoneme recognition by introducing a recurrent ladder network, achieving fully-supervised baseline performance with only 75% of labels on the TIMIT corpus.
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.