Low-Order Spherical Harmonic HRTF Restoration Using a Neural Network Approach

Applied Sciences

Gavin Kearney¹  Benjamin Tsui¹  WilliamA. P. Smith² 

[1] AudioLab, Communications Technologies Research Group, Department of Electronic Engineering, University of York, York YO10 5DD, UK;Computer Vision and Pattern Recognition (CVPR) Research Group in the Department of Computer Science, University of York, York YO10 5GH, UK;

关键词: deep learning;    head related transfer function (HRTF);    restoration;    ambisonics;    spatial audio;    spherical harmonic;   

DOI  :  10.3390/app10175764

来源: DOAJ

【 摘 要 】

Spherical harmonic (SH) interpolation is a commonly used method to spatially up-sample sparse head related transfer function (HRTF) datasets to denser HRTF datasets. However, depending on the number of sparse HRTF measurements and SH order, this process can introduce distortions into high frequency representations of the HRTFs. This paper investigates whether it is possible to restore some of the distorted high frequency HRTF components using machine learning algorithms. A combination of convolutional auto-encoder (CAE) and denoising auto-encoder (DAE) models is proposed to restore the high frequency distortion in SH-interpolated HRTFs. Results were evaluated using both perceptual spectral difference (PSD) and localisation prediction models, both of which demonstrated significant improvement after the restoration process.

【 授权许可】

Unknown