# Gaussian Process Models for HRTF based Sound-Source Localization and Active-Learning

arXiv: https://arxiv.org/abs/1502.03163 · HTML: https://mlsanity.com/paper/1502.03163/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Feb 2015.

## Built on by (most cited first, 1 of 1)

- [HRTF Interpolation using a Spherical Neural Process Meta-Learner](https://mlsanity.com/paper/2310.13430/) (2023)

## Abstract (arXiv)

From a machine learning perspective, the human ability localize sounds can be modeled as a non-parametric and non-linear regression problem between binaural spectral features of sound received at the ears (input) and their sound-source directions (output). The input features can be summarized in terms of the individual's head-related transfer functions (HRTFs) which measure the spectral response between the listener's eardrum and an external point in 3D. Based on these viewpoints, two related problems are considered: how can one achieve an optimal sampling of measurements for training sound-source localization (SSL) models, and how can SSL models be used to infer the subject's HRTFs in listening tests. First, we develop a class of binaural SSL models based on Gaussian process regression and solve a forward selection problem that finds a subset of input-output samples that best generalize to all SSL directions. Second, we use an active-learning approach that updates an online SSL model for inferring the subject's SSL errors via headphones and a graphical user interface. Experiments show that only a small fraction of HRTFs are required for 5circ localization accuracy and that the learned HRTFs are localized closer to their intended directions than non-individualized HRTFs.