End-to-End Multi-View Lipreading

TL;DR

This paper introduces an end-to-end multi-view lipreading system using BLSTM networks that learns directly from pixel data, effectively combining multiple views to significantly improve speech recognition accuracy.

Contribution

It presents the first model to simultaneously learn feature extraction and speech classification from multiple views in an end-to-end manner, achieving state-of-the-art results.

Findings

Achieves 96.9% accuracy on OuluVS2 database.

Improves performance by 3-3.8% over frontal view alone.

Outperforms previous multi-view lipreading methods.

Abstract

Non-frontal lip views contain useful information which can be used to enhance the performance of frontal view lipreading. However, the vast majority of recent lipreading works, including the deep learning approaches which significantly outperform traditional approaches, have focused on frontal mouth images. As a consequence, research on joint learning of visual features and speech classification from multiple views is limited. In this work, we present an end-to-end multi-view lipreading system based on Bidirectional Long-Short Memory (BLSTM) networks. To the best of our knowledge, this is the first model which simultaneously learns to extract features directly from the pixels and performs visual speech classification from multiple views and also achieves state-of-the-art performance. The model consists of multiple identical streams, one for each view, which extract features directly from different poses of mouth images. The temporal dynamics in each stream/view are modelled by a BLSTM and the fusion of multiple streams/views takes place via another BLSTM. An absolute average improvement of 3% and 3.8% over the frontal view performance is reported on the OuluVS2 database when the best two (frontal and profile) and three views (frontal, profile, 45) are combined, respectively. The best three-view model results in a 10.5% absolute improvement over the current multi-view state-of-the-art performance on OuluVS2, without using external databases for training, achieving a maximum classification accuracy of 96.9%.