Cycle-Consistent Generative Adversarial Network Architectures for Audio Visual Speech Recognition.

Yibo He Kah Phooi Seng Li-Minn Ang Xingyu Zhao

Published in: ICSPCC (2023)

Keyphrases

audio visual speech recognition
multi stream
generative model
audio visual
information retrieval
video sequences
hidden markov models
face detection
visual information