Using Active Speaker Faces for Diarization in TV shows.

Rahul Sharma Shrikanth Narayanan

Published in: CoRR (2022)

Keyphrases

speaker diarization
tv shows
closed captions
human interactions
video clips
speaker identification
speech recognition
face images
face recognition
broadcast news
text classification
human activities
human interaction
image database
low level
topic segmentation
data streams
similarity measure