Spatial grouping as a method to improve personalized head-related transfer function prediction

The head-related transfer function (HRTF) characterizes the frequency response of the sound traveling path between a specific location and the ear. When it comes to estimating HRTFs by neural network models, angle-specific models greatly outperform global models but demand high computational resources. To balance the computational resource and performance, we propose a method by grouping HRTF data spatially to reduce variance within each subspace. HRTF predicting neural network is then trained for each subspace. Results show the proposed method performs better than global models and angle-specific models by using different grouping strategies at the ipsilateral and contralateral sides.