Show simple item record

dc.contributor.authorNesbit, Aen_US
dc.contributor.authorJafari, MGen_US
dc.contributor.authorVincent, Een_US
dc.contributor.authorPlumbley, MDen_US
dc.contributor.editorWang, Wen_US
dc.date.accessioned2014-01-21T12:47:07Z
dc.date.issued2011en_US
dc.identifier.isbn1615209190en_US
dc.identifier.isbn9781615209194en_US
dc.identifier.other10
dc.identifier.other10
dc.identifier.other10en_US
dc.identifier.urihttp://qmro.qmul.ac.uk/xmlui/handle/123456789/5268
dc.descriptionThis is the author's final version of the article, first published as A. Nesbit, M. G. Jafari, E. Vincent and M. D. Plumbley. Audio Source Separation Using Sparse Representations. In W. Wang (Ed), Machine Audition: Principles, Algorithms and Systems. Chapter 10, pp. 246-264. IGI Global, 2011. ISBN 978-1-61520-919-4. DOI: 10.4018/978-1-61520-919-4.ch010
dc.descriptionfile: NesbitJafariVincentP11-audio.pdf:n\NesbitJafariVincentP11-audio.pdf:PDF owner: markp timestamp: 2011.02.04
dc.descriptionfile: NesbitJafariVincentP11-audio.pdf:n\NesbitJafariVincentP11-audio.pdf:PDF owner: markp timestamp: 2011.02.04en_US
dc.description.abstractThe authors address the problem of audio source separation, namely, the recovery of audio signals from recordings of mixtures of those signals. The sparse component analysis framework is a powerful method for achieving this. Sparse orthogonal transforms, in which only few transform coefficients differ significantly from zero, are developed; once the signal has been transformed, energy is apportioned from each transform coefficient to each estimated source, and, finally, the signal is reconstructed using the inverse transform. The overriding aim of this chapter is to demonstrate how this framework, as exemplified here by two different decomposition methods which adapt to the signal to represent it sparsely, can be used to solve different problems in different mixing scenarios. To address the instantaneous (neither delays nor echoes) and underdetermined (more sources than mixtures) mixing model, a lapped orthogonal transform is adapted to the signal by selecting a basis from a library of predetermined bases. This method is highly related to the windowing methods used in the MPEG audio coding framework. In considering the anechoic (delays but no echoes) and determined (equal number of sources and mixtures) mixing case, a greedy adaptive transform is used based on orthogonal basis functions that are learned from the observed data, instead of being selected from a predetermined library of bases. This is found to encode the signal characteristics, by introducing a feedback system between the bases and the observed data. Experiments on mixtures of speech and music signals demonstrate that these methods give good signal approximations and separation performance, and indicate promising directions for future research.en_US
dc.format.extent246 - 264 (18)en_US
dc.publisherIGI Globalen_US
dc.relation.ispartofMachine Audition: Principles, Algorithms and Systemsen_US
dc.titleAudio Source Separation Using Sparse Representationsen_US
dc.typeBook chapter
dc.identifier.doi10.4018/978-1-61520-919-4.ch010en_US
pubs.notesNot knownen_US
pubs.publication-statusPublisheden_US
pubs.publisher-urlhttp://www.igi-global.com/chapter/audio-source-separation-using-sparse/45488en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record