English

Towards Perception-Informed Latent HRTF Representations

Audio and Speech Processing 2026-01-27 v1 Sound

Abstract

Personalized head-related transfer functions (HRTFs) are essential for ensuring a realistic auditory experience over headphones, because they take into account individual anatomical differences that affect listening. Most machine learning approaches to HRTF personalization rely on a learned low-dimensional latent space to generate or select custom HRTFs for a listener. However, these latent representations are typically learned in a manner that optimizes for spectral reconstruction but not for perceptual compatibility, meaning they may not necessarily align with perceptual distance. In this work, we first study whether traditionally learned HRTF representations are well correlated with perceptual relations using auditory-based objective perceptual metrics; we then propose a method for explicitly embedding HRTFs into a perception-informed latent space, leveraging a metric-based loss function and supervision via Metric Multidimensional Scaling (MMDS). Finally, we demonstrate the applicability of these learned representations to the task of HRTF personalization. We suggest that our method has the potential to render personalized spatial audio, leading to an improved listening experience.

Keywords

Cite

@article{arxiv.2507.02815,
  title  = {Towards Perception-Informed Latent HRTF Representations},
  author = {You Zhang and Andrew Francl and Ruohan Gao and Paul Calamia and Zhiyao Duan and Ishwarya Ananthabhotla},
  journal= {arXiv preprint arXiv:2507.02815},
  year   = {2026}
}

Comments

Accepted by IEEE WASPAA 2025, camera-ready version

R2 v1 2026-07-01T03:45:19.074Z