Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognition
This addresses the need for better noise-robust speech recognition in AVSR, though it is incremental as it builds on existing fusion methods.
The paper tackled the problem of sub-optimal multimodal representations in audio-visual speech recognition (AVSR) by proposing a cross-modal global interaction and local alignment (GILA) approach, which improved noise-robustness and outperformed state-of-the-art methods on LRS3 and LRS2 benchmarks.
Audio-visual speech recognition (AVSR) research has gained a great success recently by improving the noise-robustness of audio-only automatic speech recognition (ASR) with noise-invariant visual information. However, most existing AVSR approaches simply fuse the audio and visual features by concatenation, without explicit interactions to capture the deep correlations between them, which results in sub-optimal multimodal representations for downstream speech recognition task. In this paper, we propose a cross-modal global interaction and local alignment (GILA) approach for AVSR, which captures the deep audio-visual (A-V) correlations from both global and local perspectives. Specifically, we design a global interaction model to capture the A-V complementary relationship on modality level, as well as a local alignment approach to model the A-V temporal consistency on frame level. Such a holistic view of cross-modal correlations enable better multimodal representations for AVSR. Experiments on public benchmarks LRS3 and LRS2 show that our GILA outperforms the supervised learning state-of-the-art.