@article{Hogg:2024:10.1109/TASLP.2024.3375635,
author = {Hogg, A and Jenkins, M and Liu, H and Squires, I and Cooper, S and Picinali, L},
doi = {10.1109/TASLP.2024.3375635},
journal = {IEEE Transactions on Audio, Speech and Language Processing},
pages = {2085--2099},
title = {HRTF upsampling with a generative adversarial network using a gnomonic equiangular projection},
url = {http://dx.doi.org/10.1109/TASLP.2024.3375635},
volume = {32},
year = {2024}
}

Download

TY  - JOUR
AB  - 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).
AU  - Hogg,A
AU  - Jenkins,M
AU  - Liu,H
AU  - Squires,I
AU  - Cooper,S
AU  - Picinali,L
DO  - 10.1109/TASLP.2024.3375635
EP  - 2099
PY  - 2024///
SN  - 1558-7916
SP  - 2085
TI  - HRTF upsampling with a generative adversarial network using a gnomonic equiangular projection
T2  - IEEE Transactions on Audio, Speech and Language Processing
UR  - http://dx.doi.org/10.1109/TASLP.2024.3375635
UR  - https://ieeexplore.ieee.org/abstract/document/10465588
UR  - http://hdl.handle.net/10044/1/110043
VL  - 32
ER  - 

Download