LocaGen: Sub-Sample Time-Delay Learning for Beam Localization

TL;DR

LocaGen employs machine learning trained on synthetic data to significantly enhance 2-D audio beam localization accuracy, reducing errors by about 67% on low-powered embedded systems with minimal resource impact.

Contribution

It introduces a novel sub-sample time-delay learning approach that improves localization precision in low-resource environments.

Findings

Reduces DOA error by approximately 67%.

Effective on low-powered embedded systems.

Enhances accuracy with minimal resource increase.

Abstract

The goal of LocaGen is to improve the localization performance of audio signals in the 2-D beam localization problem. LocaGen reduces sampling quantization errors through machine learning models trained on realistic synthetic data generated by a simulation. The system increases the accuracy of both direction-of-arrival (DOA) and precise location estimation of an audio beam from an array of three microphones. We demonstrate LocaGen's efficacy on a low-powered embedded system with an increased localization accuracy with a minimal increase in real-time resource usage. LocaGen was demonstrated to reduce DOA error by approximately 67% even with a microphone array of only 10 kHz in audio processing.