Variational EM for Binaural Sound-Source Separation and Localization - Archive ouverte HAL Access content directly
Conference Papers Year : 2013

Variational EM for Binaural Sound-Source Separation and Localization

(1) , (2) , (1)
1
2

Abstract

The sound-source separation and localization (SSL) problems are addressed within a unified formulation. Firstly, a mapping between white-noise source locations and binaural cues is estimated. Secondly, SSL is solved via Bayesian inversion of this mapping in the presence of multiple sparse-spectrum emitters (such as speech), noise and reverberations. We propose a variational EM algorithm which is described in detail together with initialization and convergence issues. Extensive real-data experiments show that the method outperforms the state-of-the-art both in separation and localization (azimuth and elevation).
Fichier principal
Vignette du fichier
deleforge_icassp_rev.pdf (637.71 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00823453 , version 1 (17-05-2013)

Identifiers

Cite

Antoine Deleforge, Florence Forbes, Radu Horaud. Variational EM for Binaural Sound-Source Separation and Localization. ICASSP 2013 - 38th International Conference on Acoustics, Speech, and Signal Processing, May 2013, Vancouver, Canada. pp.76-80, ⟨10.1109/ICASSP.2013.6637612⟩. ⟨hal-00823453⟩
400 View
507 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More