Mirage: 2D Source Localization Using Microphone Pair Augmentation with Echoes

TL;DR

This paper introduces MIRAGE, a novel approach that leverages echoes in microphone array augmentation to improve 2D sound source localization, enabling elevation estimation with only two microphones.

Contribution

It proposes a learning-based echo estimation combined with physics-based echo aggregation, turning echoes from a hindrance into a beneficial feature for SSL.

Findings

Achieves similar azimuth accuracy to correlation-based methods

Enables elevation estimation with only two microphones

Demonstrates effectiveness in simulated reflective scenarios

Abstract

It is commonly observed that acoustic echoes hurt performance of sound source localization (SSL) methods. We introduce the concept of microphone array augmentation with echoes (MIRAGE) and show how estimation of early-echo characteristics can in fact benefit SSL. We propose a learning-based scheme for echo estimation combined with a physics-based scheme for echo aggregation. In a simple scenario involving 2 microphones close to a reflective surface and one source, we show using simulated data that the proposed approach performs similarly to a correlation-based method in azimuth estimation while retrieving elevation as well from 2 microphones only, an impossible task in anechoic settings.