利用去噪扩散模型实现HRTF个性化
Towards HRTF Personalization using Denoising Diffusion Models
AI总结：
本文提出利用去噪扩散模型基于人体测量数据生成个性化HRTF，实现沉浸式音频中的双耳渲染。
摘要：
头相关传输函数（HRTF）在沉浸式音频场景中的真实渲染中有根本性应用。然而，它们高度依赖于个体，因为它们会根据耳朵、头部和躯干的形状显著变化。因此，需要进行个性化处理以实现准确的双耳渲染。最近，去噪扩散概率模型（DDPMs），一种生成学习技术，已被应用于解决各种信号处理问题。在本文中，我们提出了一种使用DDPMs进行个性化HRTF生成的方法，该方法基于人体测量数据生成HRTF的时间域表示——头相关冲击响应（HRIR）。结果表明，DDPMs在HRTF个性化中的可行性，其性能与最先进的模型相当。
英文摘要：
Head-Related Transfer Functions (HRTFs) have fundamental applications for realistic rendering in immersive audio scenarios. However, they are strongly subject-dependent as they vary considerably depending on the shape of the ears, head and torso. Thus, personalization procedures are required for accurate binaural rendering. Recently, Denoising Diffusion Probabilistic Models (DDPMs), a class of generative learning techniques, have been applied to solve a variety of signal processing-related problems. In this paper, we propose a first approach for using DDPM conditioned on anthropometric measurements to generate personalized Head-Related Impulse Response (HRIR), the time-domain representation of HRTF. The results show the feasibility of DDPMs for HRTF personalization obtaining performance in line with state-of-the-art models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
