Paper Info
Title
Automatic Music Genre Classification Based on Modulation Spectral Analysis of Spectral and Cepstral Features
Abstract
In this paper, we will propose an automatic music genre classification approach based on long-term modulation spectral analysis of spectral (OSC and MPEG-7 NASE) as well as cepstral (MFCC) features. Modulation spectral analysis of every feature value will generate a corresponding modulation spectrum and all the modulation spectra can be collected to form a modulation spectrogram which exhibits the time-varying or rhythmic information of music signals. Each modulation spectrum is then decomposed into several logarithmically-spaced modulation subbands. The modulation spectral contrast (MSC) and modulation spectral valley (MSV) are then computed from each modulation subband. Effective and compact features are generated from statistical aggregations of the MSCs and MSVs of all modulation subbands. An information fusion approach which integrates both feature level fusion method and decision level combination method is employed to improve the classification accuracy. Experiments conducted on two different music datasets have shown that our proposed approach can achieve higher classification accuracy than other approaches with the same experimental setup.
Year
DOI
Venue
2009
10.1109/TMM.2009.2017635
IEEE Transactions on Multimedia
Keywords
Field
DocType
Spectral analysis,Cepstral analysis,Multiple signal classification,Humans,Databases,MPEG 7 Standard,Mel frequency cepstral coefficient,Signal generators,Spectrogram,Fusion power generation
Mel-frequency cepstrum,Pattern recognition,Musical acoustics,Computer science,Spectrogram,Signal generator,Cepstrum,Modulation,Speech recognition,Sensor fusion,Artificial intelligence,Frequency modulation
Journal
Volume
Issue
ISSN
11
4
1520-9210
Citations 
PageRank 
References 
50
1.62
27
Authors
4
Name
Order
Citations
PageRank
Chang-Hsing Lee143931.86
Jau-Ling Shih221711.64
Kun-Ming Yu325827.07
Hwai-San Lin4542.33