Metraipolis › archive › dc_b26f69a2fdb1
SAIL: Spatial Audio Intelligence with Large Language Models via Disentangled Acoustic-Spatial Encoding and Dual-Stream Q-Former — arXiv:2609.34347
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34347
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:02:25.324Z
- SHA-256 of the archived text
69a700601a7d60a3d117c482f85d42b5550583886b2fc8188e37ced098320786- Stable URL of this page
https://metraipolis.com/documento/dc_b26f69a2fdb1
How to cite
SAIL: Spatial Audio Intelligence with Large Language Models via Disentangled Acoustic-Spatial Encoding and Dual-Stream Q-Former — arXiv:2609.34347 — arXiv (en), https://arxiv.org/abs/2609.34347 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b26f69a2fdb1 (Metraipolis archive dc_b26f69a2fdb1, sha256 69a700601a7d60a3d117c482f85d42b5550583886b2fc8188e37ced098320786)
BibTeX
@misc{dcb26f69a2fdb1,
title = {SAIL: Spatial Audio Intelligence with Large Language Models via Disentangled Acoustic-Spatial Encoding and Dual-Stream Q-Former — arXiv:2609.34347},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34347},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b26f69a2fdb1; sha256 69a700601a7d60a3d117c482f85d42b5550583886b2fc8188e37ced098320786},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34347. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Spatial audio large language models (LLMs) enable embodied agents, wearable assistants, and immersive systems to recognize sound events, localize sources, and reason about their spatial relationships. However, existing spatial audio LLMs often rely on early fusion of acoustic and spatial features and source-agnostic token representations. These designs make it difficult to preserve the correspondence between individual sound events and their spatial attributes, particularly in multi-source scenes. To address this limitation, we propose SAIL, a Spatial Audio Intelligence framework with LLMs that preserves acoustic-spatial structure and source-level correspondence from audio encoding to LLM alignment. SAIL introduces a Disentangled Spatial Audio Transformer that represents Mel-spectrogram and interaural phase difference features as separate acoustic and spatial streams. Source-discriminative task queries further learn event, direction, and distance information for each source. A Dual-Stream Q-Former then aligns the two streams with the LLM using acoustic and spatial queries organized by source slots. Compared with the early-fusion baseline, SAIL achieves consistent improvements in dual-source sound event detection, direction and distance estimation, and spatial reasoning. These results demonstrate the importance of structured, source-discriminative audio representations for multi-source spatial understanding and reasoning. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Sound (cs.SD) ; Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2609.34347 — 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 2026-10-07T20:29:02.946Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).