Musical Source Separation using Generalised Non-negative Tensor Factorisation Models

Authors

Eugene Coyle, Technological University DublinFollow
Derry Fitzgerald, Cork Institute of TechnologyFollow
Matt Cranitch, Cork Institute of TechnologyFollow

Document Type

Conference Paper

Rights

This item is available under a Creative Commons License for non-commercial use only

Publication Details

Presented at the Workshop on Music and Machine Learning, International Conference on Machine Learning, Helsinki, 2008 http://www.audioresearchgroup.com/

Abstract

A shift-invariant non-negative tensor factorisation algorithm for musical source separation is proposed which generalises previous work by allowing each source to have its own parameters rather a fixed set of parameters for all sources. This allows independent control of the number of allowable notes, number of harmonics and shifts in time for each source. This increased flexibility allows the incorporation of further information about the sources and results in improved separation and resynthesis of the separated sources.

Recommended Citation

Coyle, E., Fitzgerald, D. & Cranitch, M. Musical source separation using generalised non-negative tensor factorisation models. Presented at the Workshop on Music and Machine Learning, International Conference on Machine Learning, Helsinki, 2008. http://www.audioresearchgroup.com/