Distributed Acoustic Mixture-of-Experts for Spatial Sound Estimation
IEEE Open Journal of Signal Processing · 2026 · 7 · 569-580
DOI: 10.1109/ojsp.2026.3693608 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Open Journal of Signal Processing, 2026. Verfasst von Gioele Greco und 3 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: REPERTORIUM, Horizon Europe. Cluster II. Culture, Creativity and Inclusive Society, Multilayered Urban Sustainability Action.
Abstract (Originalsprache)
Accurate spatial acoustic characterization is crucial for immersive audio applications, such as virtual and augmented reality, which require low-latency, high-fidelity rendering of sound fields. Traditional approaches, including physics-based simulations and centralized deep learning models, face significant challenges in scalability, data efficiency, and robustness under sparse measurement conditions, and typically require retraining or fine-tuning whenever new measurements are acquired. This paper introduces DAME, a Distributed Acoustic Mixture-of-Experts framework for large-area spatial acoustic modeling. DAME decomposes the global sound field reconstruction task into localized sub-problems, each handled by a compact neural expert trained on region-specific data, while a lightweight gating network combines the experts' predictions based on spatial queries. Unlike state-of-the-art methods, the framework supports incremental expansion on the receiver side. Specifically, new experts can be added to cover previously unsampled regions, and only the gating network is updated, avoiding full retraining of the model and preserving previously learned behavior. Evaluated on both simulated and real-world higher-order Ambisonics room impulse responses, DAME consistently outperforms state-of-the-art parametric, kernel-based, and physics-informed baselines in terms of reconstruction accuracy, directional estimation, and energy decay preservation. Computational analysis demonstrates its suitability for low-latency operation, and a perceptual evaluation confirms superior audio quality and spatial fidelity. The framework therefore provides a scalable, data-efficient alternative for robust spatial audio reconstruction in challenging sparse-data regimes.
Förderung
- REPERTORIUM
- Horizon Europe. Cluster II. Culture, Creativity and Inclusive Society
- Multilayered Urban Sustainability Action
- European Commission
Zitieren
APA
Greco, G., Zhang, D., Pezzoli, M., & Antonacci, F. (2026). Distributed Acoustic Mixture-of-Experts for Spatial Sound Estimation. IEEE Open Journal of Signal Processing, 7, 569-580. https://doi.org/10.1109/ojsp.2026.3693608
Vancouver
Greco G, Zhang D, Pezzoli M, Antonacci F. Distributed Acoustic Mixture-of-Experts for Spatial Sound Estimation. IEEE Open Journal of Signal Processing. 2026;7:569-580. doi:10.1109/ojsp.2026.3693608
BibTeX
@article{Greco2026,
author = {Greco, Gioele and Zhang, Dongzhe and Pezzoli, Mirco and Antonacci, Fabio},
title = {Distributed Acoustic Mixture-of-Experts for Spatial Sound Estimation},
journal = {IEEE Open Journal of Signal Processing},
year = {2026},
volume = {7},
pages = {569--580},
doi = {10.1109/ojsp.2026.3693608}
}
EUVIMED