AMBIT：用可执行 ScenePlans 与自蒸馏 Transfusion 实现空间音频生成与编辑

View PDF HTML (experimental)

Abstract:Spatial audio authoring coordinates source decisions with soundfield synthesis. For editing, plans specify what to change and retain, while reference audio supplies further acoustic detail. We present AMBIT, a unified framework for native First-Order Ambisonics (FOA) generation and editing with three connected contributions. First, a shared Transfusion backbone couples autoregressive planning with rectified-flow rendering through executable ScenePlans that specify source content, activity, and 3D trajectories. For editing, the plan describes the full target scene, including retained sources; contrastive features ground the requested change, while full reference latents supply residual acoustic detail for preservation. Second, an FOA-aware continuous VAE combines shared-decoder omnidirectional recovery, asymmetric grouped KL, and spatial covariance matching to preserve content and inter-channel structure. Third, joint Transfusion on-policy self-distillation (OPSD) refines planning on student-generated prefixes and rendering at sampling states reached under student plans, with target-conditioned teachers supervising both modes of the shared student. Evaluations across speech, music, and sound show improved generation content and spatial quality, acoustic fidelity during instruction-guided editing, and unedited-source preservation over the compared baselines. Project page: this https URL

Comments:	28 pages, 2 figures
Subjects:	Sound (cs.SD); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2610.34415 [cs.SD]
	(or arXiv:2610.34415v1 [cs.SD] for this version)
	https://doi.org/10.48550/arXiv.2610.34415 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Kam Man Wu [view email]
[v1] Sun, 25 Oct 2026 16:13:07 UTC (1,747 KB)