On Data-Driven Approaches to Head-Related-Transfer Function Personalization
×
Cite This
Citation & Abstract
H. Fayek, L. van der Maaten, G. Romigh, and R. Mehra, "On Data-Driven Approaches to Head-Related-Transfer Function Personalization," Paper 9890, (2017 October.). doi:
H. Fayek, L. van der Maaten, G. Romigh, and R. Mehra, "On Data-Driven Approaches to Head-Related-Transfer Function Personalization," Paper 9890, (2017 October.). doi:
Abstract: Head-Related Transfer Function (HRTF) personalization is key to improving spatial audio perception and localization in virtual auditory displays. We investigate the task of personalizing HRTFs from anthropometric measurements, which can be decomposed into two sub tasks: Interaural Time Delay (ITD) prediction and HRTF magnitude spectrum prediction. We explore both problems using state-of-the-art Machine Learning (ML) techniques. First, we show that ITD prediction can be significantly improved by smoothing the ITD using a spherical harmonics representation. Second, our results indicate that prior unsupervised dimensionality reduction-based approaches may be unsuitable for HRTF personalization. Last, we show that neural network models trained on the full HRTF representation improve HRTF prediction compared to prior methods.
@article{fayek2017on,
author={fayek, haytham and van der maaten, laurens and romigh, griffin and mehra, ravish},
journal={journal of the audio engineering society},
title={on data-driven approaches to head-related-transfer function personalization},
year={2017},
volume={},
number={},
pages={},
doi={},
month={october},}
@article{fayek2017on,
author={fayek, haytham and van der maaten, laurens and romigh, griffin and mehra, ravish},
journal={journal of the audio engineering society},
title={on data-driven approaches to head-related-transfer function personalization},
year={2017},
volume={},
number={},
pages={},
doi={},
month={october},
abstract={head-related transfer function (hrtf) personalization is key to improving spatial audio perception and localization in virtual auditory displays. we investigate the task of personalizing hrtfs from anthropometric measurements, which can be decomposed into two sub tasks: interaural time delay (itd) prediction and hrtf magnitude spectrum prediction. we explore both problems using state-of-the-art machine learning (ml) techniques. first, we show that itd prediction can be significantly improved by smoothing the itd using a spherical harmonics representation. second, our results indicate that prior unsupervised dimensionality reduction-based approaches may be unsuitable for hrtf personalization. last, we show that neural network models trained on the full hrtf representation improve hrtf prediction compared to prior methods.},}
TY - paper
TI - On Data-Driven Approaches to Head-Related-Transfer Function Personalization
SP -
EP -
AU - Fayek, Haytham
AU - van der Maaten, Laurens
AU - Romigh, Griffin
AU - Mehra, Ravish
PY - 2017
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - October 2017
TY - paper
TI - On Data-Driven Approaches to Head-Related-Transfer Function Personalization
SP -
EP -
AU - Fayek, Haytham
AU - van der Maaten, Laurens
AU - Romigh, Griffin
AU - Mehra, Ravish
PY - 2017
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - October 2017
AB - Head-Related Transfer Function (HRTF) personalization is key to improving spatial audio perception and localization in virtual auditory displays. We investigate the task of personalizing HRTFs from anthropometric measurements, which can be decomposed into two sub tasks: Interaural Time Delay (ITD) prediction and HRTF magnitude spectrum prediction. We explore both problems using state-of-the-art Machine Learning (ML) techniques. First, we show that ITD prediction can be significantly improved by smoothing the ITD using a spherical harmonics representation. Second, our results indicate that prior unsupervised dimensionality reduction-based approaches may be unsuitable for HRTF personalization. Last, we show that neural network models trained on the full HRTF representation improve HRTF prediction compared to prior methods.
Head-Related Transfer Function (HRTF) personalization is key to improving spatial audio perception and localization in virtual auditory displays. We investigate the task of personalizing HRTFs from anthropometric measurements, which can be decomposed into two sub tasks: Interaural Time Delay (ITD) prediction and HRTF magnitude spectrum prediction. We explore both problems using state-of-the-art Machine Learning (ML) techniques. First, we show that ITD prediction can be significantly improved by smoothing the ITD using a spherical harmonics representation. Second, our results indicate that prior unsupervised dimensionality reduction-based approaches may be unsuitable for HRTF personalization. Last, we show that neural network models trained on the full HRTF representation improve HRTF prediction compared to prior methods.
Authors:
Fayek, Haytham; van der Maaten, Laurens; Romigh, Griffin; Mehra, Ravish
Affiliations:
Oculus Research and Facebook, Redmond, WA, USA; Facebook AI Research, New York, NY, USA; Oculus Research, Redmond, WA, USA(See document for exact affiliation information.)
AES Convention:
143 (October 2017)
Paper Number:
9890
Publication Date:
October 8, 2017Import into BibTeX
Subject:
Spatial Audio—Part 2
Permalink:
http://www.aes.org/e-lib/browse.cfm?elib=19287