Sciweavers

ICASSP
2009
IEEE
13 years 11 months ago
Multi-modal speaker diarization of real-world meetings using compressed-domain video features
Speaker diarization is originally defined as the task of determining “who spoke when” given an audio track and no other prior knowledge of any kind. The following article sho...
Gerald Friedland, Hayley Hung, Chuohao Yeo