Neural network for multi-exponential sound energy decay analysis
Götz G, Falcón Pérez R, Schlecht SJ, Pulkki V (2022)
Publication Type: Journal article
Publication year: 2022
Journal
Book Volume: 152
Pages Range: 942-953
Journal Issue: 2
DOI: 10.1121/10.0013416
Abstract
An established model for sound energy decay functions (EDFs) is the superposition of multiple exponentials and a noise term. This work proposes a neural-network-based approach for estimating the model parameters from EDFs. The network is trained on synthetic EDFs and evaluated on two large datasets of over 20 000 EDF measurements conducted in various acoustic environments. The evaluation shows that the proposed neural network architecture robustly estimates the model parameters from large datasets of measured EDFs while being lightweight and computationally efficient. An implementation of the proposed neural network is publicly available.
Involved external institutions
Finland (FI)How to cite
APA:
Götz, G., Falcón Pérez, R., Schlecht, S.J., & Pulkki, V. (2022). Neural network for multi-exponential sound energy decay analysis. Journal of the Acoustical Society of America, 152(2), 942-953. https://dx.doi.org/10.1121/10.0013416
MLA:
Götz, Georg, et al. "Neural network for multi-exponential sound energy decay analysis." Journal of the Acoustical Society of America 152.2 (2022): 942-953.
BibTeX: Download