Efficient Audiovisual Fusion for Active Speaker Detection.

Fiseha B. Tesema Jason Gu Wei Song Hong Wu Shiqiang Zhu Zheyuan Lin

Published in: IEEE Access (2023)

Keyphrases

audio visual
automatic detection
video recordings
detection algorithm
computationally efficient
data fusion
detection rate
detection accuracy
detection method
data sets
visual information
multi modal fusion
fusion algorithm
information fusion
remote sensing
metadata
neural network