Modeling of Individual HRTFs based on Spatial Principal Component Analysis
share
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 objective experiments' results show that the HRTFs generated by the proposed method perform better than the generic method and similar to the PCA method. Meanwhile, eighteen subjects participated in the subjective experiments, and the results indicate that the localization performance of the proposed method is desired in both the azimuth localization and the elevation localization.
READ FULL TEXT
