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

Sung Jin Um Dongjin Kim Jung Uk Kim

Published in: CoRR (2023)

Keyphrases

audio visual
sound source
source localization
multi modal
visual information
spatial data
focus of attention
multimedia
multi stream
visual data
speech signal
data sets
visual attention
audio visual speech recognition
high level
spatial relationships