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 contribu...
Kam-Man Wu, Yu Zhang, Peng Fang et al.· 0 citations
SwanWeave is presented, the first one-stage multi-task framework for instruction-guided 3D FOA spatial audio editing, and introduces Spatial Preference Optimization (SPO), a Direct Preference Optimization (DPO)-based alignment objective with edit-specific negative targets, and adopts staged training to improve natural-...
Ke Lei, Chenyuhao Wen, Yu Zhang et al.· 1 citation· ⚡1
SwanTale is proposed, a multi-speaker expressive speech and audio generation model that supports both zero-shot and instruct tasks, and adopts reward-conditioned quality control and Engram conditioning along with Unified MoE for multi-task and multi-audio-modality modeling.
Yu Zhang, Ruiqi Li, Changhao Pan et al.· 3 citations
Spatial-Omni is a lightweight method that implements SO-Encoder to inject First-Order Ambisonics (FOA) spatial audio into existing Omni LLMs as an independent modality, without modifying their original audio encoders.
