Towards HRTF Personalization using Denoising Diffusion Models

TL;DR

This paper introduces a novel approach using denoising diffusion probabilistic models conditioned on anthropometric data to generate personalized HRTFs, demonstrating promising results comparable to current state-of-the-art methods.

Contribution

It is the first to apply DDPMs for HRTF personalization based on anthropometric measurements, advancing personalized audio rendering techniques.

Findings

DDPMs can generate personalized HRIRs effectively.

Performance is comparable to existing state-of-the-art models.

The approach demonstrates feasibility for practical HRTF customization.

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.