Metraipolis › archive › dc_02a7938ecaa9

AudioSphere: Towards Self-Supervised Spatial Audio Representation Models — arXiv:2611.09275

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.09275
License (as archived)
CC0-1.0
Archived
2026-11-09T22:34:56.695Z
SHA-256 of the archived text
368a2a28439a684e6b210727648caab20b3902f73a237eba5ccbf496f84eca6c
Stable URL of this page
https://metraipolis.com/documento/dc_02a7938ecaa9

How to cite

AudioSphere: Towards Self-Supervised Spatial Audio Representation Models — arXiv:2611.09275 — arXiv (en), https://arxiv.org/abs/2611.09275 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_02a7938ecaa9 (Metraipolis archive dc_02a7938ecaa9, sha256 368a2a28439a684e6b210727648caab20b3902f73a237eba5ccbf496f84eca6c)
BibTeX
@misc{dc02a7938ecaa9,
  title = {AudioSphere: Towards Self-Supervised Spatial Audio Representation Models — arXiv:2611.09275},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09275},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_02a7938ecaa9; sha256 368a2a28439a684e6b210727648caab20b3902f73a237eba5ccbf496f84eca6c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09275. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent audio embedding models learn representations that transfer across clip- and frame-level tasks, yet they operate almost exclusively on single-channel signals and are blind to spatial structure. Spatial audio models capture that structure but rely on clip-level supervision or contrastive objectives, yielding embeddings unsuitable for frame-level tasks like sound event detection and localization (SELD). We argue this dichotomy is not fundamental: patch-level spatial self-supervision can jointly learn acoustic and spatial features at both temporal granularities. We introduce AudioSphere, a multi-channel masked autoencoder trained on Ambisonics recordings that reconstructs both spectral content and directional cues via a joint spatiotemporal masking strategy that masks both time-frequency patches and intensity vectors. AudioSphere supports frame-level predictions while producing strong clip-level representations via aggregation. Alongside the model, we release RealSELD, a standardized benchmark for evaluating frozen backbones on real-world multi-channel SELD. AudioSphere enables, for the first time, SELD with a frozen self-supervised backbone, while matching or exceeding prior self-supervised audio embedding models on clip-level classification tasks spanning environmental sound, speech, and music, and on frame-level sound event detection. All code and data are available at this https URL and this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Sound (cs.SD) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.09275 — 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 2026-11-09T22:30:47.324Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).