Room dimension and boundary condition inference using room transfer functions

Yuanxin Xia; Allan Peter Engsig-Karup; Cheol-Ho Jeong

Room dimension and boundary condition inference using room transfer functions

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

178 Downloads (Orbit)

Abstract

The estimation of the absorption coefficients of the boundary surfaces in a room is important in room acoustic engineering. This research presents a machine learning method learns from simulated data to estimate the room dimensions and frequency-dependent absorption coefficients. We employ multi-task convolutional neural networks for inferring the frequency-dependent absorption coefficients and the dimensions of the room from transfer functions calculated by wave-based room acoustic methods. The proposed method provides reasonably accurate estimation of the boundary conditions and dimensions.

Original language	English
Title of host publication	Proceedings of 10^th Convention of the European Acoustics Association
Number of pages	5
Publication date	2023
Publication status	Published - 2023
Event	10th Convention of the European Acoustics Association - Politecnico di Torino, Torino, Italy Duration: 11 Sept 2023 → 15 Sept 2023 https://www.fa2023.org/

Conference

Conference	10th Convention of the European Acoustics Association
Location	Politecnico di Torino
Country/Territory	Italy
City	Torino
Period	11/09/2023 → 15/09/2023
Internet address	https://www.fa2023.org/

Keywords

Machine learning
Absorption coefficient
Room dimension
Room transfer functions

Access to Document

FulltextFinal published version, 540 KB

OpenUrl availability

Check availability in DTU Findit

Cite this

@inproceedings{ddd983cbfe45406ca17bc3ca982461e7,

title = "Room dimension and boundary condition inference using room transfer functions",

abstract = "The estimation of the absorption coefficients of the boundary surfaces in a room is important in room acoustic engineering. This research presents a machine learning method learns from simulated data to estimate the room dimensions and frequency-dependent absorption coefficients. We employ multi-task convolutional neural networks for inferring the frequency-dependent absorption coefficients and the dimensions of the room from transfer functions calculated by wave-based room acoustic methods. The proposed method provides reasonably accurate estimation of the boundary conditions and dimensions.",

keywords = "Machine learning, Absorption coefficient, Room dimension, Room transfer functions",

author = "Yuanxin Xia and Engsig-Karup, \{Allan Peter\} and Cheol-Ho Jeong",

year = "2023",

language = "English",

booktitle = "Proceedings of 10th Convention of the European Acoustics Association",

note = "10th Convention of the European Acoustics Association, EAA 2023 ; Conference date: 11-09-2023 Through 15-09-2023",

url = "https://www.fa2023.org/",

}

TY - GEN

T1 - Room dimension and boundary condition inference using room transfer functions

AU - Xia, Yuanxin

AU - Engsig-Karup, Allan Peter

AU - Jeong, Cheol-Ho

PY - 2023

Y1 - 2023

N2 - The estimation of the absorption coefficients of the boundary surfaces in a room is important in room acoustic engineering. This research presents a machine learning method learns from simulated data to estimate the room dimensions and frequency-dependent absorption coefficients. We employ multi-task convolutional neural networks for inferring the frequency-dependent absorption coefficients and the dimensions of the room from transfer functions calculated by wave-based room acoustic methods. The proposed method provides reasonably accurate estimation of the boundary conditions and dimensions.

AB - The estimation of the absorption coefficients of the boundary surfaces in a room is important in room acoustic engineering. This research presents a machine learning method learns from simulated data to estimate the room dimensions and frequency-dependent absorption coefficients. We employ multi-task convolutional neural networks for inferring the frequency-dependent absorption coefficients and the dimensions of the room from transfer functions calculated by wave-based room acoustic methods. The proposed method provides reasonably accurate estimation of the boundary conditions and dimensions.

KW - Machine learning

KW - Absorption coefficient

KW - Room dimension

KW - Room transfer functions

M3 - Article in proceedings

BT - Proceedings of 10th Convention of the European Acoustics Association

T2 - 10th Convention of the European Acoustics Association

Y2 - 11 September 2023 through 15 September 2023

ER -

Room dimension and boundary condition inference using room transfer functions

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this