Towards HRTF Personalization using Denoising Diffusion Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908682757865472 |
|---|---|
| author | Sánchez, Juan Camilo Albarracín Comanducci, Luca Pezzoli, Mirco Antonacci, Fabio |
| author_facet | Sánchez, Juan Camilo Albarracín Comanducci, Luca Pezzoli, Mirco Antonacci, Fabio |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_02871 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards HRTF Personalization using Denoising Diffusion Models Sánchez, Juan Camilo Albarracín Comanducci, Luca Pezzoli, Mirco Antonacci, Fabio Sound Audio and Speech Processing 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. |
| title | Towards HRTF Personalization using Denoising Diffusion Models |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2501.02871 |