Spatial Transfusion: From Structured Spatial Scene Understanding to Generation and Editing
cs.SD, cs.AI, eess.AS
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- Spatial-Omni: Spatial Audio Understanding Integration in Multimodal LLMs via FOA Encoding
- UAT: Unified Audio-Text Diffusion for Audio Generation, Editing, and Captioning
- Emerging Properties in Unified Multimodal Pretraining
- Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
- Classifier-Free Diffusion Guidance
- Compression of Higher Order Ambisonics with Multichannel RVQGAN
- Sensitivity Analysis of Generative Spatial Audio Metrics: A Study on Responsiveness, Smoothness, and Symmetry
Related papers
- Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play
- MuLaCover: Flexible Cover Song Generation via Symbolic Tonal Control
- Optimising Neural Speech Codecs for 300bps Communication using Reinforcement Learning
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems