Skip to Main content Skip to Navigation
Conference papers

Notes on nonnegative tensor factorization of the spectrogram for audio source separation : statistical insights and towards self-clustering of the spatial cues

Cédric Févotte 1 Alexey Ozerov 2
2 METISS - Speech and sound data modeling and processing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Nonnegative tensor factorization (NTF) of multichannel spectrograms under PARAFAC structure has recently been proposed by Fitzgerald et al as a mean of performing blind source separation (BSS) of multichannel audio data. In this paper we investigate the statistical source models implied by this approach. We show that it implicitly assumes a nonpoint-source model contrasting with usual BSS assumptions and we clarify the links between the measure of fit chosen for the NTF and the implied statistical distribution of the sources. While the original approach of Fitzgeral et al requires a posterior clustering of the spatial cues to group the NTF components into sources, we discuss means of performing the clustering within the factorization. In the results section we test the impact of the simplifying nonpoint-source assumption on underdetermined linear instantaneous mixtures of musical sources and discuss the limits of the approach for such mixtures.
Complete list of metadata

Cited literature [19 references]  Display  Hide  Download

https://hal.inria.fr/inria-00553355
Contributor : Alexey Ozerov <>
Submitted on : Friday, January 7, 2011 - 11:37:53 AM
Last modification on : Tuesday, June 15, 2021 - 4:23:07 PM
Long-term archiving on: : Friday, April 8, 2011 - 2:26:14 AM

File

FevotteOzerov_CMMR10.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00553355, version 1

Citation

Cédric Févotte, Alexey Ozerov. Notes on nonnegative tensor factorization of the spectrogram for audio source separation : statistical insights and towards self-clustering of the spatial cues. 7th International Symposium on Computer Music Modeling and Retrieval (CMMR 2010), Oct 2010, Málaga, Spain. pp.www.cmmr2010.etsit.uma.es. ⟨inria-00553355⟩

Share

Metrics

Record views

469

Files downloads

563