Frequency-Independent Ambisonics Upscaling using Deep Learning

Authors:

Chatzimoustafa, E. ,  Jax, P.

Book Title:

Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

Organization:

IEEE

Publisher:

IEEE

Pages:

p.p. 4586-4590

Date:

2026

ISBN:

979-8-33156-701-9

ISSN:

2379-190X

DOI:

10.1109/ICASSP55912.2026.11464166

Language:

English

Abstract

Due to its flexibility, the higher-order Ambisonics (HOA) sound format is widely used in spatial audio applications like virtual reality (VR). The spatial accuracy is sensitive to the HOA order, which is limited by the recording and reproduction hardware. To enhance accuracy, the directional audio coding (DirAC) method prioritizes the improvement of perceptual quality over physically accurate spatial representations. We propose a novel neural network architecture that performs HOA upscaling within frequency subbands independently by leveraging the properties of spherical harmonics basis functions that are inherent in the HOA transformations. Although the proposed network is trained on synthetic data, a 63% variance reduction of the spatial similarity is achieved compared to DirAC, while both methods exhibit similar average performance for real-world measurement data. This makes our model beneficial for applications which require reliable spatial representations.

Download

BibTeX

Copyright © by IEEE
chatzimoustafa26a.pdf

© 2026 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

---