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 10th 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 |
Keywords
- Machine learning
- Absorption coefficient
- Room dimension
- Room transfer functions