RIR-Mega: a large-scale simulated room impulse response dataset for machine learning and room acoustics modeling

TL;DR

RIR-Mega is a comprehensive, large-scale simulated room impulse response dataset designed to facilitate machine learning applications and room acoustics research, with tools for validation and baseline performance benchmarks.

Contribution

The paper introduces RIR-Mega, a large, publicly available simulated RIR dataset with a standardized metadata schema and baseline tools for machine learning and acoustics modeling.

Findings

Baseline regression model achieves MAE of 0.013 s

Dataset includes 50,000 RIRs with diverse configurations

Tools for validation and reuse are provided

Abstract

Room impulse responses are a core resource for dereverberation, robust speech recognition, source localization, and room acoustics estimation. We present RIR-Mega, a large collection of simulated RIRs described by a compact, machine friendly metadata schema and distributed with simple tools for validation and reuse. The dataset ships with a Hugging Face Datasets loader, scripts for metadata checks and checksums, and a reference regression baseline that predicts RT60 like targets from waveforms. On a train and validation split of 36,000 and 4,000 examples, a small Random Forest on lightweight time and spectral features reaches a mean absolute error near 0.013 s and a root mean square error near 0.022 s. We host a subset with 1,000 linear array RIRs and 3,000 circular array RIRs on Hugging Face for streaming and quick tests, and preserve the complete 50,000 RIR archive on Zenodo. The dataset and code are public to support reproducible studies.