Online Localization of Multiple Moving Speakers in Reverberant Environments

Xiaofei Li, Bastien Mourgue, Laurent Girin, Sharon Gannot, Radu Horaud

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

This paper addresses the problem of online multiple moving speakers localization in reverberant environments. The direct-path relative transfer function (DP-RTF), as defined by the ratio between the first taps of the convolutive transfer function (CTF) of two microphones, encodes the inter-channel direct-path information and is thus used as a localization feature being robust against reverberation. The CTF estimation is based on the cross-relation method. In this work, the recursive least-square method is proposed to solve the cross-relation problem, due to its relatively low computational cost and its good convergence rate. The DP-RTF feature estimated at each time-frequency bin is assumed to correspond to a single speaker. A complex Gaussian mixture model is used to assign each observed feature to one among several speakers. The recursive expectation-maximization algorithm is adopted to update online the model parameters. The method is evaluated with a new dataset containing multiple moving speakers, where the ground-truth speaker trajectories are recorded with a motion capture system.

Original languageEnglish
Title of host publication2018 IEEE 10th Sensor Array and Multichannel Signal Processing Workshop, SAM 2018
PublisherIEEE Computer Society
Pages405-409
Number of pages5
ISBN (Print)9781538647523
DOIs
StatePublished - 27 Aug 2018
Event10th IEEE Sensor Array and Multichannel Signal Processing Workshop, SAM 2018 - Sheffield, United Kingdom
Duration: 8 Jul 201811 Jul 2018

Publication series

NameProceedings of the IEEE Sensor Array and Multichannel Signal Processing Workshop
Volume2018-July
ISSN (Electronic)2151-870X

Conference

Conference10th IEEE Sensor Array and Multichannel Signal Processing Workshop, SAM 2018
Country/TerritoryUnited Kingdom
CitySheffield
Period8/07/1811/07/18

Bibliographical note

Publisher Copyright:
© 2018 IEEE.

Funding

This research has received funding from the ERC Advanced Grant VHIA (#340113).

FundersFunder number
Seventh Framework Programme340113
European Commission

    Keywords

    • Multiple moving speakers
    • Reverberant environnements
    • Sound-source localization

    Fingerprint

    Dive into the research topics of 'Online Localization of Multiple Moving Speakers in Reverberant Environments'. Together they form a unique fingerprint.

    Cite this