Virutal Autoencoder based Recommendation System for Individualizing Head-related Transfer Functions
We propose a virtual autoencoder based recommendation system for learning a user’s Head-related Transfer Functions (HRTFs) without subjecting a listener to impulse response or anthropometric measurements. Autoencoder neural-networks generalize principal component analysis (PCA) and learn non-linear feature spaces that supports both out-of-sample embedding and reconstruction; this may be applied to developing a more expressive low-dimensional HRTF representation. One application is to individualize HRTFs by tuning along the autoencoder feature spaces. We demonstrate this new approach by developing a virtual (black-box) user that can localize sound from query HRTFs reconstructed from those spaces. Standard optimization methods tune the autoencoder features based on the virtual user’s feedback. Experiments with CIPIC HRTFs show that the virtual user can localize along out-of-sample directions and that optimization in the autoencoder feature space improves upon initial non-individualized HRTFs. Other applications of the representation are also discussed.
