@INPROCEEDINGS{1040Samour2007,
	AUTHOR = {Amjad Samour and Mustafa Karaman and Lutz Goldmann and Thomas Sikora},
	TITLE = {Video to the Rescue of Audio: Shot Boundary Assisted Speaker Change Detection},
	BOOKTITLE = {Multimedia Content Access: Algorithms and Systems,  IS&T/SPIE's Electronic Imaging 2007},
	YEAR = {2007},
	MONTH = jan,
	EDITOR = {Alan Hanjalic; Raimondo Schettini; Nicu Sebe},
	PUBLISHER = {SPIE},
	ORGANIZATION = {SPIE},
	ADDRESS = {San Jose, CA, USA},
	NOTE = {ISBN: 9780819466198},
	PDF = {http://elvera.nue.tu-berlin.de/files/1040Samour2007.pdf},
	DOI = {10.1117/12.703114},
	URL = {http://elvera.nue.tu-berlin.de/files/1040Samour2007.pdf},
	ABSTRACT = {Speaker change detection (SCD) is a preliminary step for many audio applications such as speaker segmentation and recognition. Thus, its robustness is crucial to achieve a good performance in the later steps. Especially, misses (false negatives) affect the results. For some applications, domain-specific characteristics can be used to improve the reliability of the SCD. In broadcast news and discussions, the cooccurrence of shot boundaries and change points provides a robust clue for speaker changes. In this paper, two multimodal approaches are presented that utilize the results of a shot boundary detection (SBD) step to improve the robustness of the SCD. Both approaches clearly outperform the audio-only approach and are exclusively applicable for TV broadcast news and plenary discussions.}
}