TY - GEN
T1 - A FULLY DIFFERENTIABLE MODEL FOR UNSUPERVISED SINGING VOICE SEPARATION
AU - Richard, Gaël
AU - Chouteau, Pierre
AU - Torres, Bernardo
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024/1/1
Y1 - 2024/1/1
N2 - A novel model was recently proposed by Schulze-Forster et al. in [1] for unsupervised music source separation. This model allows to tackle some of the major shortcomings of existing source separation frameworks. Specifically, it eliminates the need for isolated sources during training, performs efficiently with limited data, and can handle homogeneous sources (such as singing voice). But, this model relies on an external multipitch estimator and incorporates an Ad hoc voice assignment procedure. In this paper, we propose to extend this framework and to build a fully differentiable model by integrating a multipitch estimator and a novel differentiable assignment module within the core model. We show the merits of our approach through a set of experiments, and we highlight in particular its potential for processing diverse and unseen data.
AB - A novel model was recently proposed by Schulze-Forster et al. in [1] for unsupervised music source separation. This model allows to tackle some of the major shortcomings of existing source separation frameworks. Specifically, it eliminates the need for isolated sources during training, performs efficiently with limited data, and can handle homogeneous sources (such as singing voice). But, this model relies on an external multipitch estimator and incorporates an Ad hoc voice assignment procedure. In this paper, we propose to extend this framework and to build a fully differentiable model by integrating a multipitch estimator and a novel differentiable assignment module within the core model. We show the merits of our approach through a set of experiments, and we highlight in particular its potential for processing diverse and unseen data.
KW - Unsupervised source separation
KW - deep learning
KW - differentiable models
KW - multiple singing voices
U2 - 10.1109/ICASSP48485.2024.10447244
DO - 10.1109/ICASSP48485.2024.10447244
M3 - Conference contribution
AN - SCOPUS:85195417020
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 946
EP - 950
BT - 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024
Y2 - 14 April 2024 through 19 April 2024
ER -