Scene-Aware Audio Rendering via Deep Acoustic Analysis

TL;DR

This paper introduces a deep learning-based method to analyze and replicate the acoustic properties of real-world rooms for realistic audio rendering using commodity devices.

Contribution

It proposes a novel approach to estimate room acoustic material properties from recorded audio and geometric models, enabling realistic virtual sound rendering.

Findings

Accurately estimates reverberation time and equalization from audio recordings.

Effectively reproduces room acoustics for virtual sound sources.

User study confirms perceptual similarity between real and rendered audio.

Abstract

We present a new method to capture the acoustic characteristics of real-world rooms using commodity devices, and use the captured characteristics to generate similar sounding sources with virtual models. Given the captured audio and an approximate geometric model of a real-world room, we present a novel learning-based method to estimate its acoustic material properties. Our approach is based on deep neural networks that estimate the reverberation time and equalization of the room from recorded audio. These estimates are used to compute material properties related to room reverberation using a novel material optimization objective. We use the estimated acoustic material characteristics for audio rendering using interactive geometric sound propagation and highlight the performance on many real-world scenarios. We also perform a user study to evaluate the perceptual similarity between the recorded sounds and our rendered audio.