In this section
@inproceedings{Hu:2024,
author = {Hu, X and Li, J and Picinali, L and Hogg, A},
pages = {396--403},
publisher = {University of Surrey},
title = {HRTF spatial upsampling in the spherical harmonics domain employing a generative adversarial network},
url = {https://www.axdesign.co.uk/publications/hrtf-spatial-upsampling-in-the-spherical-harmonics-domain-employing-a-generative-adversarial-network},
year = {2024}
}
TY - CPAPER
AB - A Head-Related Transfer Function (HRTF) is able to capture alterations a sound wave undergoes from its source before it reaches the entrances of a listener’s left and right ear canals, and is imperative for creating immersive experiences in virtual and augmented reality (VR/AR). Nevertheless, creating personalized HRTFs demands sophisticated equipment and is hindered by time-consuming data acquisition processes. To counteract these challenges, various techniques for HRTF interpolation and up-sampling have been proposed. This paper illustrates how Generative Adversarial Networks (GANs) can be applied to HRTF data upsampling in the spherical harmonics domain. We propose using Autoencoding Generative Adversarial Networks (AE-GAN) to upsample low-degree spherical harmonics coefficients and get a more accurate representation of the full HRTF set. The proposed method is bench-marked against two baselines: barycentric interpolation and HRTFselection. Results from log-spectral distortion (LSD) evaluation suggest that the proposed AE-GAN has significant potential for upsampling very sparse HRTFs, achieving 17% improvement over baseline methods.
AU - Hu,X
AU - Li,J
AU - Picinali,L
AU - Hogg,A
EP - 403
PB - University of Surrey
PY - 2024///
SP - 396
TI - HRTF spatial upsampling in the spherical harmonics domain employing a generative adversarial network
UR - https://www.axdesign.co.uk/publications/hrtf-spatial-upsampling-in-the-spherical-harmonics-domain-employing-a-generative-adversarial-network
UR - http://hdl.handle.net/10044/1/112397
ER -
Dyson School of Design Engineering
Imperial College London
25 Exhibition Road
South Kensington
London
SW7 2DB
design.engineering@imperial.ac.uk
Tel: +44 (0) 20 7594 8888