Dal Santo G, Prawda K, Schlecht SJ, Välimäki V (2024)
Publication Type: Conference contribution
Publication year: 2024
Publisher: IEEE Computer Society
Pages Range: 1409-1413
Conference Proceedings Title: Conference Record - Asilomar Conference on Signals, Systems and Computers
Event location: Hybrid, Pacific Grove, CA, USA
ISBN: 9798350354058
DOI: 10.1109/IEEECONF60004.2024.10943013
Automatic tuning of reverberation algorithms relies on the optimization of a loss function. While general audio similarity metrics are useful, they are not optimized for the specific statistical properties of reverberation in rooms. This paper presents two novel metrics for assessing the similarity of late reverberation in room impulse responses. These metrics are differentiable and can be utilized within a machine-learning framework. We compare the performance of these metrics to two popular audio metrics using a large dataset of room impulse responses encompassing various room configurations and microphone positions. The results indicate that the proposed functions based on averaged power and frequency-band energy decay outperform the baselines with the former exhibiting the most suitable profile towards the minimum. The proposed work holds promise as an improvement to the design and evaluation of reverberation similarity metrics.
APA:
Dal Santo, G., Prawda, K., Schlecht, S.J., & Välimäki, V. (2024). Similarity Metrics for Late Reverberation. In Michael B. Matthews (Eds.), Conference Record - Asilomar Conference on Signals, Systems and Computers (pp. 1409-1413). Hybrid, Pacific Grove, CA, USA: IEEE Computer Society.
MLA:
Dal Santo, Gloria, et al. "Similarity Metrics for Late Reverberation." Proceedings of the 58th Asilomar Conference on Signals, Systems and Computers, ACSSC 2024, Hybrid, Pacific Grove, CA, USA Ed. Michael B. Matthews, IEEE Computer Society, 2024. 1409-1413.
BibTeX: Download