Presentation

· Contributors · Organizations · Search Program · My Schedule · Happening Now · Maps

DiffSound: Differentiable Modal Sound Rendering and Inverse Rendering for Diverse Inference Tasks

DescriptionWe propose DiffSound, a differentiable sound rendering framework for physics-based modal sound synthesis, which consists of an implicit shape representation, a high-order finite element analysis module, and a differentiable audio synthesizer. Our framework can solve diverse inverse problems, including physical parameter estimation, geometric shape reasoning, and impact position prediction.

Authors

University of Maryland College Park

Stanford University