Fusing audio and video information for online speaker diarization.

Joerg Schmalenstroeer Martin Kelling Volker Leutnant Reinhold Haeb-Umbach

Published in: INTERSPEECH (2009)

Keyphrases

visual data
multimedia data
multimedia information
multimedia
neural network
video sequences
feature space
k means
mutual information
video data
visual information
temporal information
audio stream