Picture for Liangfa Wei

Liangfa Wei

Attentive Fusion Enhanced Audio-Visual Encoding for Transformer Based Robust Speech Recognition

Add code
Aug 06, 2020
Figure 1 for Attentive Fusion Enhanced Audio-Visual Encoding for Transformer Based Robust Speech Recognition
Figure 2 for Attentive Fusion Enhanced Audio-Visual Encoding for Transformer Based Robust Speech Recognition
Figure 3 for Attentive Fusion Enhanced Audio-Visual Encoding for Transformer Based Robust Speech Recognition
Figure 4 for Attentive Fusion Enhanced Audio-Visual Encoding for Transformer Based Robust Speech Recognition
Viaarxiv icon