Room Impulse Response Completion Using Signal-Prediction Diffusion Models Conditioned on Simulated Early Reflections

TL;DR

This paper introduces a diffusion-based method for completing room impulse responses by conditioning on simulated early reflections, improving realism and flexibility over existing techniques.

Contribution

The proposed approach combines signal-prediction diffusion models with geometric simulations, removing fixed duration constraints and enhancing RIR realism.

Findings

Outperforms state-of-the-art baseline in RIR completion

Achieves better energy decay curve reconstruction

Effectively guides generation toward realistic RIRs

Abstract

Room impulse responses (RIRs) are fundamental to audio data augmentation, acoustic signal processing, and immersive audio rendering. While geometric simulators such as the image source method (ISM) can efficiently generate early reflections, they lack the realism of measured RIRs due to missing acoustic wave effects. We propose a diffusion-based RIR completion method using signal-prediction conditioned on ISM-simulated direct-path and early reflections. Unlike state-of-the-art methods, our approach imposes no fixed duration constraint on the input early reflections. We further incorporate classifier-free guidance to steer generation toward a target distribution learned from physically realistic RIRs simulated with the Treble SDK. Objective evaluation demonstrates that the proposed method outperforms a state-of-the-art baseline in early RIR completion and energy decay curve reconstruction.