In the context of building acoustics and the acoustic diagnosis of an existing room, it introduces and investigates a new approach to estimate the mean absorption coefficients solely from a room impulse response (RIR). This inverse problem is tackled via virtually supervised learning, namely, the RIR-to-absorption mapping is implicitly learned by regression on a simulated dataset using artificial neural networks. Simple models based on well-understood architectures are the focus of this work. The critical choices of geometric, acoustic, and simulation parameters, which are used to train the models, are extensively discussed and studied while keeping in mind the conditions that are representative of the field of building acoustics. Estimation errors from the learned neural models are compared to those obtained with classical formulas that require knowledge of the room's geometry and reverberation times. Extensive comparisons made on a variety of simulated test sets highlight different conditions under which the learned models can overcome the well-known limitations of the diffuse sound field hypothesis underlying these formulas. Results obtained on real RIRs measured in an acoustically configurable room show that at 1 kHz and above, the proposed approach performs comparably to classical models when reverberation times can be reliably estimated and continues to work even when they cannot.
Skip Nav Destination
Article navigation
August 2021
August 20 2021
Mean absorption estimation from room impulse responses using virtually supervised learninga)
Special Collection:
Machine Learning in Acoustics
Cédric Foy;
Cédric Foy
1
Unité mixte de recherche en acoustique environnementale (UMR AE), Cerema, Université Gustave Eiffel
, Institut français des sciences et technologies des transports (Ifsttar), Strasbourg, 67035, France
Search for other works by this author on:
Antoine Deleforge;
Antoine Deleforge
b)
2
Université de Lorraine, Centre national de la recherche scientifique (CNRS), Inria
, Laboratoire lorrain de recherche en informatique et ses applications (LORIA), Nancy, F-54000, France
Search for other works by this author on:
Diego Di Carlo
Diego Di Carlo
3
Université Rennes, Inria, CNRS
, Institut de recherche en informatique et systèmes alétoires (IRISA), France
Search for other works by this author on:
b)
Electronic mail: antoine.deleforge@inria.fr, ORCID: 0000-0003-0339-7472.
a)
This paper is part of a special issue on Machine Learning in Acoustics.
J. Acoust. Soc. Am. 150, 1286–1299 (2021)
Article history
Received:
February 01 2021
Accepted:
July 28 2021
Citation
Cédric Foy, Antoine Deleforge, Diego Di Carlo; Mean absorption estimation from room impulse responses using virtually supervised learning. J. Acoust. Soc. Am. 1 August 2021; 150 (2): 1286–1299. https://doi.org/10.1121/10.0005888
Download citation file:
Sign in
Don't already have an account? Register
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
Sign in via your Institution
Sign in via your InstitutionPay-Per-View Access
$40.00
Citing articles via
Related Content
Performances on engine-out emissions and combustion of ethylene glycol monobutyl ether palm oil monoester as a newtype biodiesel
J. Renewable Sustainable Energy (October 2012)
Experts’ selection in the application of fuzzy fault tree analysis to evaluate an RSG – GAS primary cooling system
AIP Conference Proceedings (October 2018)
Physics in the evening
Physics Today (January 1983)
Treasurer, study groups and committees report
Physics Today (May 1975)
POPA takes its first steps
Physics Today (May 1975)