# End-To-End Visual Speech Recognition With LSTMs

## TL;DR

This paper introduces an end-to-end LSTM-based visual speech recognition system that learns features directly from mouth images and achieves state-of-the-art results by jointly modeling feature extraction and classification.

## Contribution

It presents the first model to simultaneously learn feature extraction and classification from raw pixels using LSTMs, improving performance over previous methods.

## Key findings

- 9.7% accuracy improvement on OuluVS2 database
- 1.5% accuracy improvement on CUAVE database
- First joint learning model for feature extraction and classification in visual speech recognition

## Abstract

Traditional visual speech recognition systems consist of two stages, feature extraction and classification. Recently, several deep learning approaches have been presented which automatically extract features from the mouth images and aim to replace the feature extraction stage. However, research on joint learning of features and classification is very limited. In this work, we present an end-to-end visual speech recognition system based on Long-Short Memory (LSTM) networks. To the best of our knowledge, this is the first model which simultaneously learns to extract features directly from the pixels and perform classification and also achieves state-of-the-art performance in visual speech classification. The model consists of two streams which extract features directly from the mouth and difference images, respectively. The temporal dynamics in each stream are modelled by an LSTM and the fusion of the two streams takes place via a Bidirectional LSTM (BLSTM). An absolute improvement of 9.7% over the base line is reported on the OuluVS2 database, and 1.5% on the CUAVE database when compared with other methods which use a similar visual front-end.