Presentation

NeuralSound: Learning-based Modal Sound Synthesis With Acoustic Transfer
SessionRoundtable Session: Benchmarks, Datasets and Learning
Authors
Xutong Jin
Sheng Li
Dinesh Manocha
Guoping Wang
Event Type
Technical Paper
Keywords
Animation/Simulation
Interest Areas
Research & Education
Presentation Types
In Person
Registration Categories
Full Conference Supporter
Full Conference
Exhibitor Additional Full Conference
Exhibitor Full Conference
Recordings
This session WILL NOT be recorded.
TimeWednesday, 10 August 202211:22am - 11:30am PDT
LocationEast Building, Room 1-3
DescriptionWe present a novel learning-based modal sound synthesis approach that includes a mixed vibration solver for modal analysis and an end-to-end sound radiation network for acoustic transfer. The overall running time of our method for any new object is less than one second while maintaining high sound quality.
Authors
Xutong Jin
Peking University
Sheng Li
Peking University
Dinesh Manocha
University of Maryland College Park
Guoping Wang
Peking University