Abstract
Room Impulse Responses (RIRs) characterize acoustic environments and are crucial in multiple audio signal processing tasks. High-quality RIR estimates drive applications such as virtual microphones, sound source localization, augmented reality, and data augmentation. However, obtaining RIR measurements with high spatial resolution is resource-intensive, making it impractical for large spaces or when dense sampling is required. This research addresses the challenge of estimating RIRs at unmeasured locations within a room using Denoising Diffusion Probabilistic Models (DDPM). Our method leverages the analogy between RIR matrices and image inpainting, transforming RIR data into a format suitable for diffusion-based reconstruction. Using simulated RIR data based on the image method, we demonstrate our approach's effectiveness on microphone arrays of different curvatures, from linear to semi-circular. Our method successfully reconstructs missing RIRs, even in large gaps between microphones. Under these conditions, it achieves accurate reconstruction, significantly outperforming baseline Spline Cubic Interpolation in terms of Normalized Mean Square Error and Cosine Distance between actual and interpolated RIRs. This research highlights the potential of using generative models for effective RIR interpolation, paving the way for generating additional data from limited real-world measurements.
Abstract (translated)
房间脉冲响应（RIR）描述了声学环境，并在多个音频信号处理任务中至关重要。高质量的RIR估计可以驱动虚拟麦克风、声音源定位、增强现实和数据增强等应用。然而，以高空间分辨率获取RIR测量非常耗费资源，在大型空间或需要密集采样的情况下，这种方法难以实施。这项研究旨在使用去噪扩散概率模型（DDPM）解决在房间内未测量位置估计RIR的挑战。我们的方法利用了RIR矩阵与图像修复之间的类比，将RIR数据转换为适合基于扩散重建的形式。通过基于影像法的模拟RIR数据，我们在不同曲率的话筒阵列上展示了我们方法的有效性，从线性到半圆形不等。即使在话筒之间有较大间隔的情况下，我们的方法也能成功地重建缺失的RIR。在这种条件下，它实现了准确的重构，在归一化均方误差和实际与插值RIR之间的余弦距离方面，远优于基线样条三次插值方法。这项研究展示了使用生成模型进行有效的RIR插值的巨大潜力，并为从有限的实际测量中生成额外数据铺平了道路。
URL
https://arxiv.org/abs/2504.20625
