@conference {126, title = {Low-latency Bass Separation using Harmonic-Percussion Decomposition}, booktitle = {International Conference on Digital Audio Effects Conference (DAFx-13)}, year = {2013}, month = {02/09/2013}, address = {Maynooth, Ireland}, abstract = {

Many recent approaches to musical source separation rely on model-based inference methods that take into account the signal{\textquoteright}s harmonic structure. To address the particular case of low-latency bass separation, we propose a method that combines harmonic decomposition using a Tikhonov regularization-based algorithm, with the peak contrast analysis of the pitch likelihood function. Our experiment compares the separation performance of this method to a naive low-pass filter, a state-of-the-art NMF-based method and a near-optimal binary mask. The proposed low-latency method achieves results similar to the NMF-based high-latency approach at a lower computational cost. Therefore the method is valid for real-time implementations.

}, url = {http://dafx13.nuim.ie/papers/11.dafx2013_submission_13.pdf}, author = {Marxer, R. and Janer, J.} } @conference {132, title = {Study of regularizations and constraints in NMF-based drums monaural separation}, booktitle = {International Conference on Digital Audio Effects Conference (DAFx-13)}, year = {2013}, month = {09/2013}, abstract = {

Drums modelling is of special interest in musical source separation because of its widespread presence in western popular music. Current research has often focused on drums separation without specifically modelling the other sources present in the signal. This paper presents an extensive study of the use of regularizations and constraints to drive the factorization towards the separation between percussive and non-percussive music accompaniment. The proposed regularizations control the frequency smoothness of the basis components and the temporal sparseness of the gains. We also evaluated the use of temporal constraints on the gains to perform the separation, using both ground truth manual annotations (made publicly available) and automatically extracted transients. Objective evaluation of the results shows that, while optimal regularizations are highly dependent on the signal, drum event position contains enough information to achieve a high quality separation.

}, keywords = {drums, NMF, source Separation}, url = {http://dafx13.nuim.ie/papers/16.dafx2013_submission_16.pdf}, author = {Marxer, R. and Janer, J.} }