Litcius/Paper detail

HRTF Upsampling With a Generative Adversarial Network Using a Gnomonic Equiangular Projection

Aidan O. T. Hogg, Mads Jenkins, He Liu, Isaac Squires, Samuel J. Cooper, Lorenzo Picinali

2024IEEE/ACM Transactions on Audio Speech and Language Processing27 citationsDOIOpen Access PDF

Abstract

An individualised (HRTF) is very important for creating realistic (VR) and (AR) environments. However, acoustically measuring high-quality HRTFs requires expensive equipment and an acoustic lab setting. To overcome these limitations and to make this measurement more efficient HRTF upsampling has been exploited in the past where a high-resolution HRTF is created from a low-resolution one. This paper demonstrates how (GAN) can be applied to HRTF upsampling. We propose a novel approach that transforms the HRTF data for direct use with a convolutional (SRGAN). This new approach is benchmarked against three baselines: barycentric upsampling, (SH) upsampling and an HRTF selection approach. Experimental results show that the proposed method outperforms all three baselines in terms of (LSD) and localisation performance using perceptual models when the input HRTF is sparse (less than 20 measured positions).

Topics & Concepts

Equiangular polygonUpsamplingProjection (relational algebra)Generative adversarial networkGenerative grammarArtificial intelligenceMathematicsComputer scienceAdversarial systemComputer visionAlgorithmImage (mathematics)GeometryMonotone polygonAdvanced Image Processing TechniquesAdvanced Vision and ImagingImage and Signal Denoising Methods
HRTF Upsampling With a Generative Adversarial Network Using a Gnomonic Equiangular Projection | Litcius