Room dimensions and absorption inference from room transfer function via machine learning

TL;DR

This paper introduces two methods, including a machine learning approach, to infer room dimensions and absorption properties from acoustic transfer functions, aiding acoustic design and renovation with minimal data.

Contribution

It presents a novel machine learning method using multi-task CNNs for estimating room geometry and surface absorption from transfer functions, enhancing acoustic analysis capabilities.

Findings

Machine learning accurately predicts room dimensions and absorption coefficients.

Neural networks trained on simulated data generalize well to real measurements.

Methods facilitate room acoustic simulations with limited data.

Abstract

The inference of the absorption configuration of an existing room solely using acoustic signals can be challenging. This research presents two methods for estimating the room dimensions and frequency-dependent absorption coefficients using room transfer functions. The first method, a knowledge-based approach, calculates the room dimensions through damped resonant frequencies of the room. The second method, a machine learning approach, employs multi-task convolutional neural networks for inferring the room dimensions and frequency-dependent absorption coefficients of each surface. The study shows that accurate wave-based simulation data can be used to train neural networks for real-world measurements and demonstrates a potential for this algorithm to be used to estimate the boundary input data for room acoustic simulations. The proposed methods can be a valuable tool for room acoustic simulations during acoustic renovation or intervention projects, as they enable to infer the room geometry and absorption conditions with reasonably small data requirements.