Timbral modeling for music artist recognition using i-vectors

Abstract

Music artist (i.e., singer) recognition is a challenging task in Music Information Retrieval (MIR). The presence of different musical instruments, the diversity of music genres and singing techniques make the retrieval of artist-relevant information from a song difficult. Many authors tried to address this problem by using complex features or hybrid systems. In this paper, we propose new song-level timbre-related features that are built from frame-level MFCCs via so-called i-vectors. We report artist recognition results with multiple classifiers such as K-nearest neighbor, Discriminant Analysis and Naive Bayes using these new features. Our approach yields considerable improvements and outperforms existing methods. We could achieve an 84.31% accuracy using MFCC features on a 20-classes artist recognition task.

DOI: 10.1109/EUSIPCO.2015.7362591

3 Figures and Tables

Cite this paper

@article{Eghbalzadeh2015TimbralMF, title={Timbral modeling for music artist recognition using i-vectors}, author={Hamid Eghbal-zadeh and Markus Schedl and Gerhard Widmer}, journal={2015 23rd European Signal Processing Conference (EUSIPCO)}, year={2015}, pages={1286-1290} }