Audio-Visual Spatial Integration and Recursive Attention for Robust Sound Source Localization.

Sung Jin Um Dongjin Kim Jung Uk Kim

Published in: ACM Multimedia (2023)

Keyphrases

audio visual
sound source
source localization
multi modal
visual information
focus of attention
spatial information
multi stream
spatial data
pattern recognition
spatio temporal
object recognition
multimedia
visual attention
semantic information
speech recognition
audio visual speech recognition