Lip Graph Assisted Audio-Visual Speech Recognition Using Bidirectional Synchronous Fusion.

Hong Liu Zhan Chen Bing Yang

Published in: INTERSPEECH (2020)

Keyphrases

audio visual
multimodal fusion
person authentication
multi modal
audio visual speech recognition
multi stream
visual information
emotion recognition
visual data
temporal context
speaker verification
audio features
multimedia
sound source
structured data
visual speech
low level
data analysis