# Semi-Supervised Phoneme Recognition with Recurrent Ladder Networks

## TL;DR

This paper introduces a recurrent ladder network for semi-supervised phoneme recognition, demonstrating that it effectively leverages unlabeled data to achieve high accuracy with fewer labels on the TIMIT dataset.

## Contribution

The paper presents a novel recurrent ladder network architecture tailored for semi-supervised learning in phoneme recognition tasks.

## Key findings

- Outperforms baseline models with fewer labeled data
- Achieves fully-supervised performance with only 75% labels
- Effectively uses unlabeled data as a regularizer

## 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.