A Variational EM Algorithm for the Separation of Moving Sound Sources - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2015

A Variational EM Algorithm for the Separation of Moving Sound Sources

Abstract

This paper addresses the problem of separation of moving sound sources. We propose a probabilistic framework based on the complex Gaussian model combined with non-negative matrix factorization. The properties associated with moving sources are modeled using time-varying mixing filters described by a stochastic temporal process. We present a variational expectation-maximization (VEM) algorithm that employs a Kalman smoother to estimate the mixing filters. The sound sources are separated by means of Wiener filters, built from the estimators provided by the proposed VEM algorithm. Preliminary experiments with simulated data show that, while for static sources we obtain results comparable with the base-line method of Ozerov et al., in the case of moving source our method outperforms a piece-wise version of the baseline method.
Fichier principal
Vignette du fichier
DKB_et_al_Waspaa_2015_final.pdf (227.74 Ko) Télécharger le fichier
Dionyssos-Radu.pdf (560.65 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01169764 , version 1 (30-06-2015)
hal-01169764 , version 2 (05-11-2015)

Identifiers

Cite

Dionyssos Kounades-Bastian, Laurent Girin, Xavier Alameda-Pineda, Sharon Gannot, Radu Horaud. A Variational EM Algorithm for the Separation of Moving Sound Sources. WASPAA 2015 - IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, IEEE Signal Processing Society, Oct 2015, New Paltz, NY, United States. pp.1-5, ⟨10.1109/WASPAA.2015.7336936⟩. ⟨hal-01169764v2⟩
605 View
723 Download

Altmetric

Share

Gmail Facebook X LinkedIn More