Abstract
This work presents a machine-learning-based method to estimate the reverberation time of a virtual room for auralization purposes. The models take as input geometric features of the room and output the estimated reverberation time values as function of frequency. The proposed model is trained and evaluated using a novel dataset composed of real-world acoustical measurements of a single room with 832 different configurations of furniture and absorptive materials, for multiple loudspeaker positions. The method achieves a prediction accuracy
of approximately 90% for most frequency bands. Furthermore, when comparing against the Sabine and Eyring methods, the proposed approach exhibits a much higher accuracy, especially at low frequencies.
of approximately 90% for most frequency bands. Furthermore, when comparing against the Sabine and Eyring methods, the proposed approach exhibits a much higher accuracy, especially at low frequencies.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 23rd International Congress on Acoustics : integrating 4th EAA Euroregio 2019 : 9-13 September 2019 in Aachen, Germany |
| Publisher | Deutsche Gesellschaft für Akustik |
| Pages | 7258-7265 |
| ISBN (Print) | 978-3-939296-15-7 |
| Publication status | Published - 13 Sept 2019 |
| MoE publication type | A4 Conference publication |
| Event | International Congress on Acoustics - Aachen, Germany Duration: 9 Sept 2019 → 13 Sept 2019 Conference number: 23 |
Conference
| Conference | International Congress on Acoustics |
|---|---|
| Abbreviated title | ICA |
| Country/Territory | Germany |
| City | Aachen |
| Period | 09/09/2019 → 13/09/2019 |
Keywords
- reverberation time
- machine learning
- room acoustics