Robust 3D Localization and Tracking of Sound Sources Using Beamforming and Particle Filtering

TL;DR

This paper introduces a robust sound source localization and tracking system using an array of microphones, beamforming, and particle filtering, achieving high accuracy in direction and distance estimation even with multiple moving speakers in noisy settings.

Contribution

It combines RWPHAT-based beamforming with particle filtering for accurate 3D localization and tracking of multiple sound sources in real-time.

Findings

Direction accuracy better than 1 degree

Distance estimation within 10% RMS

Tracks up to three moving speakers simultaneously

Abstract

In this paper we present a new robust sound source localization and tracking method using an array of eight microphones (US patent pending) . The method uses a steered beamformer based on the reliability-weighted phase transform (RWPHAT) along with a particle filter-based tracking algorithm. The proposed system is able to estimate both the direction and the distance of the sources. In a videoconferencing context, the direction was estimated with an accuracy better than one degree while the distance was accurate within 10% RMS. Tracking of up to three simultaneous moving speakers is demonstrated in a noisy environment.