A data-driven two-microphone method for in-situ sound absorption measurements

2025-02-06

AI Summary

Accurately measuring the normal-incidence sound absorption coefficient of porous plates *in situ*—especially under the idealized infinite-size assumption—remains challenging. To address this, this paper proposes a data-driven dual-microphone method based on a one-dimensional convolutional neural network (1D-CNN), which directly predicts the infinite-size normal-incidence absorption coefficient from the two-point pressure transfer function measured on finite-sized samples. Training data are synthesized by integrating boundary element method (BEM) simulations with the Delany–Bazley–Miki (DBM) empirical model. This work pioneers the integration of deep learning into the conventional dual-microphone framework, eliminating reliance on impedance tubes and infinitely extended specimens. Experimental validation on fibrous materials demonstrates excellent agreement between predictions, theoretical values, and impedance-tube measurements, achieving a mean absolute error < 0.05. The method significantly enhances both accuracy and practicality of *in situ* acoustic absorption assessment under real-world conditions.

Technology Category

• Data Mining & Knowledge Management: Knowledge Acquisition from the Web
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

Abstract

This work presents a data-driven approach to estimating the sound absorption coefficient of an infinite porous slab using a neural network and a two-microphone measurement on a finite porous sample. A 1D-convolutional network predicts the sound absorption coefficient from the complex-valued transfer function between the sound pressure measured at the two microphone positions. The network is trained and validated with numerical data generated by a boundary element model using the Delany-Bazley-Miki model, demonstrating accurate predictions for various numerical samples. The method is experimentally validated with baffled rectangular samples of a fibrous material, where sample size and source height are varied. The results show that the neural network offers the possibility to reliably predict the in-situ sound absorption of a porous material using the traditional two-microphone method as if the sample were infinite. The normal-incidence sound absorption coefficient obtained by the network compares well with that obtained theoretically and in an impedance tube. The proposed method has promising perspectives for estimating the sound absorption coefficient of acoustic materials after installation and in realistic operational conditions.

Problem

• Estimates sound absorption coefficient using neural networks
• Uses two-microphone method for in-situ measurements
• Validates method with experimental and numerical data

Innovation

• Neural network predicts absorption coefficients
• Two-microphone method enhances measurement accuracy
• Boundary element model validates numerical data