GWA: A Large High-Quality Acoustic Dataset for Audio Processing

TL;DR

The GWA dataset offers a large collection of high-quality synthetic acoustic responses from diverse real-world environments, enabling improved audio processing and deep learning applications through accurate wave-based simulations.

Contribution

This work introduces the first dataset with precise wave acoustic simulations in complex scenes, combining geometric and wave-based modeling for audio research.

Findings

GWA dataset contains 2 million synthetic IRs from 6.8K environments.

Demonstrates improved accuracy over real-world IR recordings.

Enhances performance in speech recognition, enhancement, and separation tasks.

Abstract

We present the Geometric-Wave Acoustic (GWA) dataset, a large-scale audio dataset of about 2 million synthetic room impulse responses (IRs) and their corresponding detailed geometric and simulation configurations. Our dataset samples acoustic environments from over 6.8K high-quality diverse and professionally designed houses represented as semantically labeled 3D meshes. We also present a novel real-world acoustic materials assignment scheme based on semantic matching that uses a sentence transformer model. We compute high-quality impulse responses corresponding to accurate low-frequency and high-frequency wave effects by automatically calibrating geometric acoustic ray-tracing with a finite-difference time-domain wave solver. We demonstrate the higher accuracy of our IRs by comparing with recorded IRs from complex real-world environments. Moreover, we highlight the benefits of GWA on audio deep learning tasks such as automated speech recognition, speech enhancement, and speech separation. This dataset is the first data with accurate wave acoustic simulations in complex scenes. Codes and data are available at https://gamma.umd.edu/pro/sound/gwa.