Multimodal Integration for Large-Vocabulary Audio-Visual Speech Recognition

TL;DR

This paper investigates various multimodal integration strategies for large-vocabulary audio-visual speech recognition, emphasizing dynamic stream reliability indicators to improve robustness and accuracy in challenging conditions.

Contribution

It compares multiple integration methods for large-vocabulary speech recognition and highlights the effectiveness of dynamic stream reliability indicators in enhancing performance.

Findings

Dynamic stream reliability indicators significantly improve recognition accuracy.

Hybrid architectures benefit from visual information during audio distortions.

Early and end-to-end integration strategies are evaluated for large-vocabulary tasks.

Abstract

For many small- and medium-vocabulary tasks, audio-visual speech recognition can significantly improve the recognition rates compared to audio-only systems. However, there is still an ongoing debate regarding the best combination strategy for multi-modal information, which should allow for the translation of these gains to large-vocabulary recognition. While an integration at the level of state-posterior probabilities, using dynamic stream weighting, is almost universally helpful for small-vocabulary systems, in large-vocabulary speech recognition, the recognition accuracy remains difficult to improve. In the following, we specifically consider the large-vocabulary task of the LRS2 database, and we investigate a broad range of integration strategies, comparing early integration and end-to-end learning with many versions of hybrid recognition and dynamic stream weighting. One aspect, which is shown to provide much benefit here, is the use of dynamic stream reliability indicators, which allow for hybrid architectures to strongly profit from the inclusion of visual information whenever the audio channel is distorted even slightly.