Kernel additive models for source separation

Antoine Liutkus, Derry Fitzgerald, Zafar Rafii, Bryan A Pardo, Laurent Daudet

Research output: Contribution to journalArticlepeer-review

68 Scopus citations

Abstract

Source separation consists of separating a signal into additive components. It is a topic of considerable interest with many applications that has gathered much attention recently. Here, we introduce a new framework for source separation called Kernel Additive Modelling, which is based on local regression and permits efficient separation of multidimensional and/or nonnegative and/or non-regularly sampled signals. The main idea of the method is to assume that a source at some location can be estimated using its values at other locations nearby, where nearness is defined through a source-specific proximity kernel. Such a kernel provides an efficient way to account for features like periodicity, continuity, smoothness, stability over time or frequency, and self-similarity. In many cases, such local dynamics are indeed much more natural to assess than any global model such as a tensor factorization. This framework permits one to use different proximity kernels for different sources and to separate them using the iterative kernel backfitting algorithm we describe. As we show, kernel additive modelling generalizes many recent and efficient techniques for source separation and opens the path to creating and combining source models in a principled way. Experimental results on the separation of synthetic and audio signals demonstrate the effectiveness of the approach.

Original languageEnglish (US)
Article number6842708
Pages (from-to)4298-4310
Number of pages13
JournalIEEE Transactions on Signal Processing
Volume62
Issue number16
DOIs
StatePublished - Aug 15 2014

Keywords

  • Source separation
  • kernel method
  • local regression
  • nonparametric models

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Kernel additive models for source separation'. Together they form a unique fingerprint.

Cite this