@INPROCEEDINGS{0793Kim2004,
	AUTHOR = {Hyoung-Gook Kim and Thomas Sikora},
	TITLE = {Performance of MPEG-7 spectral basis representations for retrieval of home video abstract},
	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/0793Kim2004.ps},
	ABSTRACT = {In this paper, we present a classification and retrieval technique targeted for retrieval of home video abstract using dimension-reduced, decorrelated spectral features of audio content. The feature extraction based on MPEG-7 descriptors consists of three main stages: Normalized Audio Spectrum Envelope (NASE), basis decomposition algorithm and basis projection, obtained by multiplying the NASE with a set of extracted basis functions. A classifier based on continuous hidden Markov models is applied. For retrieval with accurate performance the system consists of a two-level hierarchy method using speech recognition and sound classification. For the measure of the performance we compare the classification results of MPEG-7 standardized features vs. Mel-scale Frequency Cepstrum Coefficients (MFCC). Results show that the MFCC features yield better performance compared to MPEG-7 features.}
}