Showing 2017 · cs.SDShow all
2 papers · 2 filters
cs.SD2017
Shift-Invariant Kernel Additive Modelling for Audio Source Separation
Delia Fano Yela, Sebastian Ewert, Ken O'Hanlon +1
A major goal in blind source separation to identify and separate sources is to model their inherent characteristics. While most state-of-the-art approaches are supervised methods t…
cs.SD2017
On the Importance of Temporal Context in Proximity Kernels: A Vocal Separation Case Study
Delia Fano Yela, Sebastian Ewert, Derry FitzGerald +1
Musical source separation methods exploit source-specific spectral characteristics to facilitate the decomposition process. Kernel Additive Modelling (KAM) models a source applying…