Presentation

GWA: A Large Geometric-wave Acoustic Dataset for Audio Deep Learning
SessionRoundtable Session: Benchmarks, Datasets and Learning
Authors
Zhenyu Tang
Rohith Aralikatti
Anton Ratnarajah
Dinesh Manocha
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 202211:09am - 11:14am PDT
LocationEast Building, Room 1-3
DescriptionWe present the geometric-wave acoustic (GWA) dataset, a large-scale audio dataset of over 2 million synthetic room impulse responses and their corresponding detailed geometric and simulation configurations. This is the first audio dataset that provides accurate wave acoustic simulation over 6.8K high-quality diverse 3D environments represented as semantically labeled meshes.
Authors
Zhenyu Tang
University of Maryland
Rohith Aralikatti
University of Maryland, College Park
Anton Ratnarajah
University of Maryland, College Park
Dinesh Manocha
University of Maryland