Modeling of Individual HRTFs based on Spatial Principal Component Analysis

TL;DR

This paper introduces a deep neural network-based approach for modeling individual HRTFs using spatial principal component analysis, enabling accurate prediction of HRTFs across different directions with improved performance over generic methods.

Contribution

The paper presents a novel deep neural network method that models individual HRTFs by combining spatial PCA with anthropometric data, enhancing prediction accuracy across spatial directions.

Findings

Proposed method outperforms generic HRTF methods in objective and subjective tests.

Spectral distortion is significantly reduced in high frequencies with the proposed method.

PCA-based approach shows better localization accuracy than the proposed method.

Abstract

Head-related transfer function (HRTF) plays an important role in the construction of 3D auditory display. This paper presents an individual HRTF modeling method using deep neural networks based on spatial principal component analysis. The HRTFs are represented by a small set of spatial principal components combined with frequency and individual-dependent weights. By estimating the spatial principal components using deep neural networks and mapping the corresponding weights to a quantity of anthropometric parameters, we predict individual HRTFs in arbitrary spatial directions. The objective and subjective experiments evaluate the HRTFs generated by the proposed method, the principal component analysis (PCA) method, and the generic method. The results show that the HRTFs generated by the proposed method and PCA method perform better than the generic method. For most frequencies the spectral distortion of the proposed method is significantly smaller than the PCA method in the high frequencies but significantly larger in the low frequencies. The evaluation of the localization model shows the PCA method is better than the proposed method. The subjective localization experiments show that the PCA and the proposed methods have similar performances in most conditions. Both the objective and subjective experiments show that the proposed method can predict HRTFs in arbitrary spatial directions.