Position Tracking of a Varying Number of Sound Sources with Sliding Permutation Invariant Training

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

1 Downloads (Pure)


Machine-learning-based sound source localization (SSL) methods have shown strong performance in challenging acoustic scenarios. However, little work has been done on adapting such methods to track consistently multiple sources appearing and disappearing, as would occur in reality. In this paper, we present a new training strategy for deep learning SSL models with a straightforward implementation based on the mean squared error of the optimal association between estimated and reference positions in the preceding time frames. It optimizes the desired properties of a tracking system: handling a time-varying number of sources and ordering localization estimates according to their trajectories, minimizing identity switches (IDSs). Evaluation on simulated data of multiple reverberant moving sources and on two model architectures proves its effectiveness in reducing identity switches without compromising frame-wise localization accuracy.
Original languageEnglish
Title of host publication2023 31st European Signal Processing Conference (EUSIPCO)
ISBN (Electronic)978-9-4645-9360-0
Publication statusPublished - 4 Sept 2023
Publication typeA4 Article in conference proceedings
EventEuropean Signal Processing Conference - Helsinki, Finland
Duration: 4 Sept 20238 Sept 2023

Publication series

NameEuropean Signal Processing Conference
ISSN (Electronic)2076-1465


ConferenceEuropean Signal Processing Conference

Publication forum classification

  • Publication forum level 1


Dive into the research topics of 'Position Tracking of a Varying Number of Sound Sources with Sliding Permutation Invariant Training'. Together they form a unique fingerprint.

Cite this