@INPROCEEDINGS{0778Kim2004,
	AUTHOR = {Hyoung-Gook Kim and Martin Haller and Thomas Sikora},
	TITLE = {Comparison of MPEG-7 Basis Projection Features and MFCC applied to Robust Speaker Recognition},
	BOOKTITLE = {ISCA - A Speaker Odyssey 2004},
	YEAR = {2004},
	MONTH = may,
	ADDRESS = {Toledo, Spain},
	PDF = {http://elvera.nue.tu-berlin.de/files/0778Kim2004.pdf},
	ABSTRACT = {Our purpose is to evaluate the efficiency of MPEG-7 basis projection (BP) features vs. Mel-scale Frequency Cepstrum Coefficients (MFCC) for speaker recognition in noisy environments.The MPEG-7 feature extraction mainly consists of a Normalized Audio Spectrum Envelope (NASE), a basis decomposition algorithm and a spectrum basis projection. Prior to the feature extraction the noise reduction algorithm is performed by using a modified log spectral amplitude speech estimator (LSA) and a minima controlled noise estimation (MC). The noise-reduced features can be effectively used in a HMM-based recognition system. The performance is measured by the segmental signal-to-noise ratio, and the recognition results of the MPEG-7 standardized features vs. Mel-scale Frequency Cepstrum Coefficients (MFCC) in comparison to other noise reduction methods. Results show that the MFCC features yield better performance compared to MPEG-7 features.}
}