ODYSSEY 2004 - The Speaker and Language Recognition Workshop

May 31 - June 3, 2004
Toledo, Spain

Comparison of MPEG-7 Basis Projection Features and MFCC applied to Robust Speaker Recognition

Hyoung-Gook Kim, Martin Haller, Thomas Sikora

Department of Communication Systems, Technical University of Berlin, Germany

Our purpose is to evaluate the efficiency of MPEG-7 basis projection (BP) features vs. Mel-scale Frequency Cepstrum Coef- ficients (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 signalto- noise ratio, and the recognition results of the MPEG-7 standardized features vs. Mel-scale Frequency Cepstrum Coeffi- cients (MFCC) in comparison to other noise reduction methods. Results show that the MFCC features yield better performance compared to MPEG-7 features.

Full Paper

Bibliographic reference.  Kim, Hyoung-Gook / Haller, Martin / Sikora, Thomas (2004): "Comparison of MPEG-7 basis projection features and MFCC applied to robust speaker recognition", In ODYS-2004, 275-278.