Metraipolis › archive › dc_2faf558337e1

Generative Learning for Ambisonic Upscaling — arXiv:2609.23479

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.23479
License (as archived)
CC0-1.0
Archived
2026-10-10T01:00:11.511Z
SHA-256 of the archived text
6c183b120f79b2148f42b2ca6b8c396b75b739f08d125fe653bed0a287e9f4e3
Stable URL of this page
https://metraipolis.com/documento/dc_2faf558337e1

How to cite

Generative Learning for Ambisonic Upscaling — arXiv:2609.23479 — arXiv (en), https://arxiv.org/abs/2609.23479 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2faf558337e1 (Metraipolis archive dc_2faf558337e1, sha256 6c183b120f79b2148f42b2ca6b8c396b75b739f08d125fe653bed0a287e9f4e3)
BibTeX
@misc{dc2faf558337e1,
  title = {Generative Learning for Ambisonic Upscaling — arXiv:2609.23479},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.23479},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2faf558337e1; sha256 6c183b120f79b2148f42b2ca6b8c396b75b739f08d125fe653bed0a287e9f4e3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23479. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Ambisonics Upscaling (AU) aims to enhance the spatial resolution of sound fields by estimating high-order Ambisonics (HOA) components from low-order observations. While deep learning and model-based strategies have been considered for AU, both approaches exhibit significant performance degradation in realistic scenarios, where reverberant sound fields violate the directional sparsity inherent to discriminative mappings. In this work, we address AU as a generative task rather than a deterministic reconstruction, expanding generative modeling to specifically target the recovery of spatial information in reverberant speech. We investigate two dominant continuous-time generative paradigms, adapting both Score-based Generative Model and Flow Matching to these complex acoustic settings. We provide an extensive numerical study comparing our methods against state-of-the-art baselines in various acoustic scenarios. Additionally, we conduct subjective listening tests to evaluate the perceived quality and spatial accuracy of the proposed generative framework across various reverberant scenarios. The studies reveal that Flow Matching consistently outperforms both its discriminative counterparts and Diffusion-based paradigms in all reverberant settings.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in eess.SP).
Categorie arXiv: Audio and Speech Processing (eess.AS) ; Signal Processing (eess.SP).
Pagina del lavoro: https://arxiv.org/abs/2609.23479 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T23:57:50.988Z dalla pagina https://arxiv.org/catchup/eess.SP/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).