Tracking Multiple Audio Sources with the Von Mises Distribution and Variational EM - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles IEEE Signal Processing Letters Year : 2019

Tracking Multiple Audio Sources with the Von Mises Distribution and Variational EM

Abstract

In this paper we address the problem of simultaneously tracking several moving audio sources, namely the problem of estimating source trajectories from a sequence of observed features. We propose to use the von Mises distribution to model audio-source directions of arrival with circular random variables. This leads to a Bayesian filtering formulation which is intractable because of the combinatorial explosion of associating observed variables with latent variables, over time. We propose a variational approximation of the filtering distribution. We infer a variational expectation-maximization algorithm that is both computationally tractable and time efficient. We propose an audio-source birth method that favors smooth source trajectories and which is used both to initialize the number of active sources and to detect new sources. We perform experiments with the recently released LOCATA dataset comprising two moving sources and a moving microphone array mounted onto a robot.
Fichier principal
Vignette du fichier
main_HAL.pdf (432.1 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01969050 , version 1 (21-03-2019)

Identifiers

Cite

Yutong Ban, Xavier Alameda-Pineda, Christine Evers, Radu Horaud. Tracking Multiple Audio Sources with the Von Mises Distribution and Variational EM. IEEE Signal Processing Letters, 2019, 26 (6), pp.798 - 802. ⟨10.1109/LSP.2019.2908376⟩. ⟨hal-01969050⟩
184 View
244 Download

Altmetric

Share

Gmail Facebook X LinkedIn More