HRTF upsampling with a generative adversarial network using a gnomonic equiangular projection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914692652335104 |
|---|---|
| author | Hogg, Aidan O. T. Jenkins, Mads Liu, He Squires, Isaac Cooper, Samuel J. Picinali, Lorenzo |
| author_facet | Hogg, Aidan O. T. Jenkins, Mads Liu, He Squires, Isaac Cooper, Samuel J. Picinali, Lorenzo |
| contents | An individualised head-related transfer function (HRTF) is very important for creating realistic virtual reality (VR) and augmented reality (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 generative adversarial networks (GANs) can be applied to HRTF upsampling. We propose a novel approach that transforms the HRTF data for direct use with a convolutional super-resolution generative adversarial network (SRGAN). This new approach is benchmarked against three baselines: barycentric upsampling, spherical harmonic (SH) upsampling and an HRTF selection approach. Experimental results show that the proposed method outperforms all three baselines in terms of log-spectral distortion (LSD) and localisation performance using perceptual models when the input HRTF is sparse (less than 20 measured positions). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_05812 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | HRTF upsampling with a generative adversarial network using a gnomonic equiangular projection Hogg, Aidan O. T. Jenkins, Mads Liu, He Squires, Isaac Cooper, Samuel J. Picinali, Lorenzo Audio and Speech Processing Computer Vision and Pattern Recognition Human-Computer Interaction Machine Learning Sound Signal Processing An individualised head-related transfer function (HRTF) is very important for creating realistic virtual reality (VR) and augmented reality (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 generative adversarial networks (GANs) can be applied to HRTF upsampling. We propose a novel approach that transforms the HRTF data for direct use with a convolutional super-resolution generative adversarial network (SRGAN). This new approach is benchmarked against three baselines: barycentric upsampling, spherical harmonic (SH) upsampling and an HRTF selection approach. Experimental results show that the proposed method outperforms all three baselines in terms of log-spectral distortion (LSD) and localisation performance using perceptual models when the input HRTF is sparse (less than 20 measured positions). |
| title | HRTF upsampling with a generative adversarial network using a gnomonic equiangular projection |
| topic | Audio and Speech Processing Computer Vision and Pattern Recognition Human-Computer Interaction Machine Learning Sound Signal Processing |
| url | https://arxiv.org/abs/2306.05812 |