Personalized Head-Related Transfer Function Modeling Using a Neural Operator

Lu C, McMullen K. Personalized Head-Related Transfer Function Modeling Using a Neural Operator. In: AVARIG 2026: Audio for Virtual and Augmented Reality and Immersive Games. Audio Engineering Society; 2026. Paper 10344. Available from: https://aes.org/publications/elibrary-page/?id=23306

@inproceedings{Lu2026_23306,
  author = {Lu, Chenshen and McMullen, Kyla},
  title = {{Personalized Head-Related Transfer Function Modeling Using a Neural Operator}},
  booktitle = {AVARIG 2026: Audio for Virtual and Augmented Reality and Immersive Games},
  note = {Paper 10344},
  year = {2026},
  month = jun,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=23306}
}

TY  - CPAPER
TI  - Personalized Head-Related Transfer Function Modeling Using a Neural Operator
AU  - Lu, Chenshen
AU  - McMullen, Kyla
T2  - AVARIG 2026: Audio for Virtual and Augmented Reality and Immersive Games
M1  - Paper 10344
PY  - 2026
DA  - 2026/06/30
UR  - https://aes.org/publications/elibrary-page/?id=23306
PB  - Audio Engineering Society
LA  - en
AB  - Virtual, augmented, and mixed reality experiences are becoming more commonplace as consumer-grade devices proliferate. Head-Related Transfer Functions (HRTFs) are used to create realistic spatial audio in virtual and augmented environments. Mathematically, HRTFs represent solutions to acoustic boundary-value scattering problems governed by the Helmholtz equation. Neural operators are neural networks designed to learn the solutions of partial differential equations (PDEs). The present work proposes an operator-learning framework based on the Deep Operator Network (DeepONet) for individualized HRTF prediction. By implementing a non-uniform sampling strategy for 3-D head meshes and data compression along the frequency axis, the framework achieves highfidelity predictions while reducing data dimensionality. Our method shows low log-spectral distortion, generalizes to unseen spatial grids, and infers an entire heads HRTF field in 0:3 seconds. Objective evaluations demonstrate the frameworks effectiveness in personalization and spatial interpolation. Furthermore, robust performance on unseen subjects and coordinates highlights the models generalization capability, offering a computationally efficient alternative for HRTFs personalization. Codes are available at https://github.com/chenshenlu/NOPHRTF_AES.
ER  -