Skip to Main content Skip to Navigation
Conference papers

PROJET - Spatial Audio Separation Using Projections

Abstract : We propose a projection-based method for the unmixing of multi-channel audio signals into their different constituent spatial objects. Here, spatial objects are modelled using a unified framework which handles both point sources and diffuse sources. We then propose a novel methodology to estimate and take advantage of the spatial dependencies of an object. Where previous research has processed the original multichannel mixtures directly and has been principally focused on the use of inter-channel covariance structures, here we instead process projections of the multichannel signal on many different spatial directions. These linear combinations consist of observations where some spatial objects are cancelled or enhanced. We then propose an algorithm which takes these projections as the observations, discarding dependencies between them. Since each one contains global information regarding all channels of the original multichannel mixture, this provides an effective means of learning the parameters of the original audio, while avoiding the need for joint-processing of all the channels. We further show how to recover the separated spatial objects and demonstrate the use of the technique on stereophonic music signals.
Complete list of metadatas

Cited literature [37 references]  Display  Hide  Download
Contributor : Roland Badeau <>
Submitted on : Wednesday, January 27, 2016 - 9:53:47 AM
Last modification on : Wednesday, December 18, 2019 - 5:18:45 PM
Document(s) archivé(s) le : Friday, November 11, 2016 - 4:34:06 PM


Files produced by the author(s)


  • HAL Id : hal-01248014, version 1


Derry Fitzgerald, Antoine Liutkus, Roland Badeau. PROJET - Spatial Audio Separation Using Projections. 41st International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016, Shanghai, China. ⟨hal-01248014⟩



Record views


Files downloads