English

Towards HRTF Personalization using Denoising Diffusion Models

Sound 2025-12-02 v1 Audio and Speech Processing

Abstract

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.

Keywords

Cite

@article{arxiv.2501.02871,
  title  = {Towards HRTF Personalization using Denoising Diffusion Models},
  author = {Juan Camilo Albarracín Sánchez and Luca Comanducci and Mirco Pezzoli and Fabio Antonacci},
  journal= {arXiv preprint arXiv:2501.02871},
  year   = {2025}
}

Comments

to appear in ICASSP 2025

R2 v1 2026-06-28T20:57:21.634Z