Egocentric Deep Multi-Channel Audio-Visual Active Speaker Localization.

Hao Jiang Calvin Murdock Vamsi Krishna Ithapu

Published in: CoRR (2022)

Keyphrases

audio visual
multi channel
video summarization
multi modal
speaker verification
single channel
visual information
multimedia
multi stream
person authentication
emotion recognition
activity recognition
visual data
sound source
audio features
high dimensional
image processing