Kernel Spectrogram models for source separation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

Kernel Spectrogram models for source separation


In this study, we introduce a new framework called Kernel Additive Modelling for audio spectrograms that can be used for multichannel source separation. It assumes that the spectrogram of a source at any time-frequency bin is close to its value in a neighbourhood indicated by a source-specific proximity kernel. The rationale for this model is to easily account for features like periodicity, stability over time or frequency, self-similarity, etc. 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 estimate them blindly using their mixtures only. Estimation is performed using a variant of the kernel backfitting algorithm that allows for multichannel mixtures and permits parallelization. Experimental results on the separation of vocals from musical backgrounds demonstrate the efficiency of the approach.
Fichier principal
Vignette du fichier
KAM_HSCMAv2.pdf (237.5 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00959384 , version 1 (14-03-2014)
hal-00959384 , version 2 (15-03-2014)
hal-00959384 , version 3 (21-03-2014)
hal-00959384 , version 4 (16-02-2015)


  • HAL Id : hal-00959384 , version 4


Antoine Liutkus, Zafar Rafii, Bryan Pardo, Derry Fitzgerald, Laurent Daudet. Kernel Spectrogram models for source separation. HSCMA, May 2014, Nancy, France. ⟨hal-00959384v4⟩
676 View
1144 Download


Gmail Facebook X LinkedIn More