Evaluation of MFCC estimation techniques for music similarity

Jesper Højvang Jensen, Mads Græsbøll Christensen, Manohar N. Murthi, Søren Holdt Jensen

Research output: Contribution to journalConference articlepeer-review

14 Scopus citations


Spectral envelope parameters in the form of mel-frequency cepstral coefficients are often used for capturing timbral information of music signals in connection with genre classification applications. In this paper, we evaluate mel-frequency cepstral coefficient (MFCC) estimation techniques, namely the classical FFT and linear prediction based implementations and an implementation based on the more recent MVDR spectral estimator. The performance of these methods are evaluated in genre classification using a probabilistic classifier based on Gaussian Mixture models. MFCCs based on fixed order, signal independent linear prediction and MVDR spectral estimators did not exhibit any statistically significant improvement over MFCCs based on the simpler FFT.

Original languageEnglish (US)
JournalEuropean Signal Processing Conference
StatePublished - Dec 1 2006
Event14th European Signal Processing Conference, EUSIPCO 2006 - Florence, Italy
Duration: Sep 4 2006Sep 8 2006

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering


Dive into the research topics of 'Evaluation of MFCC estimation techniques for music similarity'. Together they form a unique fingerprint.

Cite this