RealImpact: A Dataset of Impact Sound Fields for Real Objects
This provides a dataset for researchers in audio-visual learning and simulation calibration, but it is incremental as it builds on prior simulation work by focusing on real-world data.
The authors tackled the lack of a standard dataset for real object impact sounds by creating RealImpact, a large-scale dataset with 150,000 recordings of 50 everyday objects, and demonstrated its utility for evaluating simulation methods and benchmark tasks like listener location classification.
Objects make unique sounds under different perturbations, environment conditions, and poses relative to the listener. While prior works have modeled impact sounds and sound propagation in simulation, we lack a standard dataset of impact sound fields of real objects for audio-visual learning and calibration of the sim-to-real gap. We present RealImpact, a large-scale dataset of real object impact sounds recorded under controlled conditions. RealImpact contains 150,000 recordings of impact sounds of 50 everyday objects with detailed annotations, including their impact locations, microphone locations, contact force profiles, material labels, and RGBD images. We make preliminary attempts to use our dataset as a reference to current simulation methods for estimating object impact sounds that match the real world. Moreover, we demonstrate the usefulness of our dataset as a testbed for acoustic and audio-visual learning via the evaluation of two benchmark tasks, including listener location classification and visual acoustic matching.