Informed Separation of Spatial Images of Stereo Music Recordings Using Second-Order Statistics

Stanislaw Gorlow 1 Sylvain Marchand 2
2 Lab-STICC_UBO_CID_IHSEV
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance
Abstract : In this work we address a reverse audio engineering problem, i.e. the separation of stereo tracks of professionally produced music recordings. More precisely, we apply a spatial filtering approach with a quadratic constraint using an explicit source-image-mixture model. The model parameters are "learned" from a given set of original stereo tracks, reduced in size and used afterwards to demix the desired tracks in best possible quality from a preexisting mixture. Our approach implicates a side-information rate of 10 kbps per source or channel and has a low computational complexity. The results obtained for the SiSEC 2013 dataset are intended to be used as reference for comparison with unpublished approaches.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [6 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00865352
Contributor : Stanislaw Gorlow <>
Submitted on : Tuesday, September 24, 2013 - 1:36:17 PM
Last modification on : Monday, February 25, 2019 - 3:14:11 PM
Document(s) archivé(s) le : Wednesday, December 25, 2013 - 4:33:39 AM

File

Gorlow_MLSP2013.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00865352, version 1

Citation

Stanislaw Gorlow, Sylvain Marchand. Informed Separation of Spatial Images of Stereo Music Recordings Using Second-Order Statistics. 2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP), Sep 2013, Southampton, United Kingdom. pp.1-6. ⟨hal-00865352⟩

Share

Metrics

Record views

340

Files downloads

189