TY - GEN
T1 - Influence of low-level features extracted from rhythmic and harmonic sections on music genre classification
AU - Rosner, Aldona
AU - Weninger, Felix
AU - Schuller, Björn
AU - Michalak, Marcin
AU - Kostek, Bozena
N1 - Publisher Copyright:
© Springer India 2014.
PY - 2014
Y1 - 2014
N2 - We present a comprehensive evaluation of the influence of “harmonic” and rhythmic sections contained in an audio file on automatic music genre classification. The study is performed using the ISMIS database composed of music files, which are represented by vectors of acoustic parameters describing low-level music features. Non-negative Matrix Factorization serves for blind separation of instrument components. Rhythmic components are identified and separated from the rest of the audio signals. Using such separated streams, it is possible to obtain information on the influence of rhythmic and harmonic components on music genre recognition. Further, the “original” audio feature vectors stemming from the non-separated signal are extended with such that base exclusively on drum and harmonic sections. The impact of these new parameters on music genre classification is investigated comparing the “basic” k-Nearest Neighbor classifier and Support Vector Machines.
AB - We present a comprehensive evaluation of the influence of “harmonic” and rhythmic sections contained in an audio file on automatic music genre classification. The study is performed using the ISMIS database composed of music files, which are represented by vectors of acoustic parameters describing low-level music features. Non-negative Matrix Factorization serves for blind separation of instrument components. Rhythmic components are identified and separated from the rest of the audio signals. Using such separated streams, it is possible to obtain information on the influence of rhythmic and harmonic components on music genre recognition. Further, the “original” audio feature vectors stemming from the non-separated signal are extended with such that base exclusively on drum and harmonic sections. The impact of these new parameters on music genre classification is investigated comparing the “basic” k-Nearest Neighbor classifier and Support Vector Machines.
KW - Drums separation
KW - Instrument separation
KW - MIR (Music Information Retrieval)
KW - Music genre classification
UR - https://www.scopus.com/pages/publications/84927608036
U2 - 10.1007/978-3-319-02309-0_51
DO - 10.1007/978-3-319-02309-0_51
M3 - Conference contribution
AN - SCOPUS:84927608036
T3 - Advances in Intelligent Systems and Computing
SP - 467
EP - 473
BT - Man-Machine Interactions 3
A2 - Gruca, Aleksandra
A2 - Czachórski, Tadeusz
A2 - Kozielski, Stanisław
A2 - Czachórski, Tadeusz
PB - Springer Verlag
T2 - 3rd International Conference on Man-Machine Interactions, ICMMI 2013
Y2 - 22 October 2013 through 25 October 2013
ER -