TY - GEN
T1 - Gaussian mixture models for score-informed instrument separation
AU - Sprechmann, Pablo
AU - Cancela, Pablo
AU - Sapiro, Guillermo
PY - 2012
Y1 - 2012
N2 - A new framework for representing quasi-harmonic signals, and its application to score-informed single channel musical instruments separation, is introduced in this paper. In the proposed approach, the signal's pitch and spectral envelope are modeled separately. The model combines parametric filters enforcing an harmonic structure in the representation, with Gaussian modeling for representing the spectral envelope. The estimation of the signal's model is cast as an inverse problem efficiently solved via a maximum a posteriori expectation-maximization algorithm. The relation of the proposed framework with common non-negative factorization methods is also discussed. The algorithm is evaluated with both real and synthetic instruments mixtures, and comparisons with recently proposed techniques are presented.
AB - A new framework for representing quasi-harmonic signals, and its application to score-informed single channel musical instruments separation, is introduced in this paper. In the proposed approach, the signal's pitch and spectral envelope are modeled separately. The model combines parametric filters enforcing an harmonic structure in the representation, with Gaussian modeling for representing the spectral envelope. The estimation of the signal's model is cast as an inverse problem efficiently solved via a maximum a posteriori expectation-maximization algorithm. The relation of the proposed framework with common non-negative factorization methods is also discussed. The algorithm is evaluated with both real and synthetic instruments mixtures, and comparisons with recently proposed techniques are presented.
KW - audio modeling
KW - Score-informed source separation
KW - single channel source separation
UR - http://www.scopus.com/inward/record.url?scp=84867623101&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84867623101&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2012.6287814
DO - 10.1109/ICASSP.2012.6287814
M3 - Conference contribution
AN - SCOPUS:84867623101
SN - 9781467300469
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 49
EP - 52
BT - 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012 - Proceedings
T2 - 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2012
Y2 - 25 March 2012 through 30 March 2012
ER -