# HRTF Interpolation using a Spherical Neural Process Meta-Learner

arXiv: https://arxiv.org/abs/2310.13430 · HTML: https://mlsanity.com/paper/2310.13430/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 53 references that are in the map.
- First posted on arXiv 20 Oct 2023.

## Builds on (most cited first, 17 of 17)

- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Spherical CNNs](https://mlsanity.com/paper/1801.10130/) (2018)
- [Conditional Neural Processes](https://mlsanity.com/paper/1807.01613/) (2018)
- [Accurate Uncertainties for Deep Learning Using Calibrated Regression](https://mlsanity.com/paper/1807.00263/) (2018)
- [Neural Processes](https://mlsanity.com/paper/1807.01622/) (2018)
- [Learning SO(3) Equivariant Representations with Spherical CNNs](https://mlsanity.com/paper/1711.06721/) (2017)
- [Convolutional Conditional Neural Processes](https://mlsanity.com/paper/1910.13556/) (2019)
- [Evaluating and Calibrating Uncertainty Prediction in Regression Tasks](https://mlsanity.com/paper/1905.11659/) (2019)
- [Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes](https://mlsanity.com/paper/2007.01332/) (2020)
- [Spin-Weighted Spherical CNNs](https://mlsanity.com/paper/2006.10731/) (2020)
- [HRTF upsampling with a generative adversarial network using a gnomonic equiangular projection](https://mlsanity.com/paper/2306.05812/) (2023)
- [Magnitude-Corrected and Time-Aligned Interpolation of Head-Related Transfer Functions](https://mlsanity.com/paper/2303.09966/) (2023)
- [Head-Related Transfer Function Interpolation from Spatially Sparse Measurements Using Autoencoder with Source Position Conditioning](https://mlsanity.com/paper/2207.10967/) (2022)
- [HRTF Individualization: A Survey](https://mlsanity.com/paper/2003.06183/) (2020)
- [Global HRTF Interpolation via Learned Affine Transformation of Hyper-conditioned Features](https://mlsanity.com/paper/2204.02637/) (2022)
- [Gaussian Process Models for HRTF based Sound-Source Localization and Active-Learning](https://mlsanity.com/paper/1502.03163/) (2015)

## Built on by (most cited first, 2 of 2)

- [HRTF Estimation using a Score-based Prior](https://mlsanity.com/paper/2410.01562/) (2024)
- [Gaussian Process Regression of Steering Vectors With Physics-Aware Deep Composite Kernels for Augmented Listening](https://mlsanity.com/paper/2509.02571/) (2025)

## Abstract (arXiv)

Several individualization methods have recently been proposed to estimate a subject's Head-Related Transfer Function (HRTF) using convenient input modalities such as anthropometric measurements or pinnae photographs. There exists a need for adaptively correcting the estimation error committed by such methods using a few data point samples from the subject's HRTF, acquired using acoustic measurements or perceptual feedback. To this end, we introduce a Convolutional Conditional Neural Process meta-learner specialized in HRTF error interpolation. In particular, the model includes a Spherical Convolutional Neural Network component to accommodate the spherical geometry of HRTF data. It also exploits potential symmetries between the HRTF's left and right channels about the median axis. In this work, we evaluate the proposed model's performance purely on time-aligned spectrum interpolation grounds under a simplified setup where a generic population-mean HRTF forms the initial estimates prior to corrections instead of individualized ones. The trained model achieves up to 3 dB relative error reduction compared to state-of-the-art interpolation methods despite being trained using only 85 subjects. This improvement translates up to nearly a halving of the data point count required to achieve comparable accuracy, in particular from 50 to 28 points to reach an average of -20 dB relative error per interpolated feature. Moreover, we show that the trained model provides well-calibrated uncertainty estimates. Accordingly, such estimates can inform the sequential decision problem of acquiring as few correcting HRTF data points as needed to meet a desired level of HRTF individualization accuracy.