Reproduce “Audible World Models: Spatially Aware Sound Generation for 3D Worlds” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Duowen Chen, Jinjin He, Gouthaman KV, Sandeep Bangalore Venkatesh, Bo Zhu
The system represents generated-world sounds as persistent sources anchored to scene geometry, then renders them through acoustic propagation as the listener moves. A blind study of 20 scenes with 20 participants found 79.5% Rank-1 preference for the system, versus 12.5% for MMAudio; this measures preference, not objective real-world acoustic accuracy.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.