arXiv cs.AI· Kam Man Wu, Yu Zhang, Pengjun Fang, Mingfei Chen, Weijia Chen, Zeyue Tian, Qifeng Chen·· 3 小时前AI 评分30
AMBIT：基于可执行 ScenePlan 与自蒸馏 Transfusion 的空间音频生成与编辑框架
Spatial Audio Generation and Editing with Executable Plans and Self-Distilling Transfusion
AI 导读
研究者提出 AMBIT 框架，实现一阶 Ambisonics（FOA）空间音频的原生生成与编辑。该框架用共享 Transfusion 骨干将自回归规划与 rectified-flow 渲染耦合，通过可执行 ScenePlan 指定声源内容、活动状态和 3D 轨迹，编辑时对比特征锚定修改内容、参考 latent 保留其余声源。
正文 · 原文
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)
来源：arXiv cs.AI · arxiv.org