Mechatronic Generation of Datasets for Acoustics Research

TL;DR

This paper introduces MARS, a flexible, automated mechatronic system for creating large-scale, reliable spatial audio datasets through synchronized multi-robot experiments, making acoustic data collection more accessible.

Contribution

The paper presents a novel, extensible robotic platform that automates and standardizes spatial audio data collection, enabling dynamic scene experiments and remote experiment design.

Findings

MARS produces consistent audio data across repeated runs.

The system supports complex dynamic acoustic scene experiments.

MARS enhances accessibility for acoustic research without dedicated spaces.

Abstract

We address the challenge of making spatial audio datasets by proposing a shared mechanized recording space that can run custom acoustic experiments: a Mechatronic Acoustic Research System (MARS). To accommodate a wide variety of experiments, we implement an extensible architecture for wireless multi-robot coordination which enables synchronized robot motion for dynamic scenes with moving speakers and microphones. Using a virtual control interface, we can remotely design automated experiments to collect large-scale audio data. This data is shown to be similar across repeated runs, demonstrating the reliability of MARS. We discuss the potential for MARS to make audio data collection accessible for researchers without dedicated acoustic research spaces.