Dataset Augmentation and Dimensionality Reduction of Pinna-Related Transfer Functions
This work addresses the need for efficient HRTF individualization in audio applications, but it is incremental as it builds on prior dataset augmentation and applies standard PCA methods.
The authors tackled the problem of modeling inter-individual variations in pinna-related transfer functions (PRTFs) for binaural synthesis individualization by augmenting a dataset from 119 to 1005 ear shapes and PRTFs, and found that a PCA model trained on the augmented dataset performed best in dimensionality reduction across all tested component numbers.
Efficient modeling of the inter-individual variations of head-related transfer functions (HRTFs) is a key matterto the individualization of binaural synthesis. In previous work, we augmented a dataset of 119 pairs of earshapes and pinna-related transfer functions (PRTFs), thus creating a wide dataset of 1005 ear shapes and PRTFsgenerated by random ear drawings (WiDESPREaD) and acoustical simulations. In this article, we investigate thedimensionality reduction capacity of two principal component analysis (PCA) models of magnitude PRTFs, trainedon WiDESPREaD and on the original dataset, respectively. We find that the model trained on the WiDESPREaDdataset performs best, regardless of the number of retained principal components.