Description of algorithms for Ben-Gurion University Submission to the LOCATA challenge

TL;DR

This paper details algorithms for source localization in the LOCATA challenge, utilizing DOA estimation with DPD tests and clustering for accurate speaker direction determination.

Contribution

It introduces specific DPD-based methods for different microphone arrays and combines them with clustering to improve localization accuracy.

Findings

Effective DOA estimation with DPD tests for Nao and Eigenmike arrays.

Successful application of clustering to refine speaker direction estimates.

Demonstrated methods' suitability for LOCATA challenge tasks.

Abstract

This paper summarizes the methods used to localize the sources recorded for the LOCalization And TrAcking (LOCATA) challenge. The tasks of stationary sources and arrays were considered, i.e., tasks 1 and 2 of the challenge, which were recorded with the Nao robot array, and the Eigenmike array. For both arrays, direction of arrival (DOA) estimation has been performed with measurements in the short time Fourier transform domain, and with direct-path dominance (DPD) based tests, which aim to identify time-frequency (TF) bins dominated by the direct sound. For the recordings with Nao, a DPD test which is applied directly to the microphone signals was used. For the Eigenmike recordings, a DPD based test designed for plane-wave density measurements in the spherical harmonics domain was used. After acquiring DOA estimates with TF bins that passed the DPD tests, a stage of k-means clustering is performed, to assign a final DOA estimate for each speaker.