mlsanityData to 7 Oct 2026

Towards HRTF Personalization using Denoising Diffusion Models

arXiv 2501.02871 ↗First posted 6 Jan 2025cs.SD eess.AScited by 1

On the map: Diffusion models → Audio, speech and music

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 10 of its 37 references that are in the map. First posted on arXiv 6 Jan 2025.

Builds on

10 of 37 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024BUDDy: Single-Channel Blind Unsupervised Dereverberation with Diffusion Models7 May
  2. 2023Reconstruction of Sound Field through Diffusion Models14 Dec
  3. 2023Timbre transfer using image-to-image denoising diffusion implicit models10 Jul
  4. 2022Solving Audio Inverse Problems with a Diffusion Model27 Oct
  5. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesis21 Sep

Other references · 5

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2023HRTF upsampling with a generative adversarial network using a gnomonic equiangular projectioncited by 6
  5. 2024NIIRF: Neural IIR Filter Field for HRTF Upsampling and Personalizationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026HRIR-Former: Grid-Free Time-Domain Reconstruction of Head-Related Impulse Responses with a Spatially Encoded Transformercited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024HRTF Estimation using a Score-based Prior
  2. 2022BinauralGrad: A Two-Stage Conditional Diffusion Probabilistic Model for Binaural Audio Synthesis
  3. 2025Mixture-of-Experts Framework for Field-of-View Enhanced Signal-Dependent Binauralization of Moving Talkers
  4. 2023FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models
  5. 2023DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation
  6. 2026TempoSyncDiff: Distilled Temporally-Consistent Diffusion for Low-Latency Audio-Driven Talking Head Generation
  7. 2022Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors
  8. 2023MFR-Net: Multi-faceted Responsive Listening Head Generation via Denoising Diffusion Model