用扩散模型填补房间声学数据空缺，提升音频重建精度
DiffusionRIR: Room Impulse Response Interpolation using Diffusion Models
- 将混响响应矩阵类比图像修复，用扩散模型重建缺失数据
- 在麦克风间距大时仍保持低误差，均方误差和余弦距离更优
- 适合需要高密度声学采样的虚拟现实、语音增强等场景
房间混响响应（RIR）是表征声学环境的关键，对虚拟麦克风、声源定位、增强现实及数据增强等任务至关重要。但高空间分辨率的RIR测量成本高昂，难以在大空间或密集采样场景下实现。本文提出基于去噪扩散概率模型（DDPM）的RIR插值方法，将RIR矩阵视为可修复的图像，利用基于图像法生成的模拟数据，在不同曲率的麦克风阵列（从线性到半圆形）上验证有效性。结果表明，该方法能准确重建麦克风间大间隔缺失的RIR，显著优于基线三次样条插值，在归一化均方误差和实际与插值RIR间的余弦距离上表现更优。研究展示了生成模型在高效生成高质量声学数据方面的潜力，为从有限实测数据中扩展生成提供新路径。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。