@INPROCEEDINGS{0794Kim2004,
	AUTHOR = {Hyoung-Gook Kim and Thomas Sikora},
	TITLE = {Automatic segmentation of speakers in broadcast audio material},
	BOOKTITLE = {IS&T/SPIE's Electronic Imaging 2004},
	YEAR = {2004},
	MONTH = jan,
	ADDRESS = {San Jose, CA, USA},
	PDF = {http://elvera.nue.tu-berlin.de/files/0794Kim2004.ps},
	ABSTRACT = {In this paper, dimension-reduced, decorrelated spectral features for general sound recognition are applied to segment conversational speech of both broadcast news audio and panel discussion television programs. Without a priori information about number of speakers, the audio stream is segmented by a hybrid metric-based and model-based segmentation algorithm. For the measure of the performance we compare the segmentation results of the hybrid method versus metric-based segmentation with both the MPEG-7 standardized features and Mel-scale Frequency Cepstrum Coefficients (MFCC). Results show that the MFCC features yield better performance compared to MPEG-7 features. The hybrid approach significantly outperforms direct metric based segmentation.}
}