AES E-Library

S. Kaneko, T. Suenaga, and S. Sekine, "DeepEarNet: Individualizing Spatial Audio with Photography, Ear Shape Modeling, and Neural Networks," Paper 6-3, (2016 September.). doi: S. Kaneko, T. Suenaga, and S. Sekine, "DeepEarNet: Individualizing Spatial Audio with Photography, Ear Shape Modeling, and Neural Networks," Paper 6-3, (2016 September.). doi:
Abstract: Individualizing spatial audio is of crucial importance for high-quality virtual and augmented reality audio. In this paper we propose a method for individualizing spatial audio by combining the recently proposed ear shape modeling technique with computer vision and machine learning. We use a convolutional neural network to obtain estimates of the ear shape model parameters from stereo photographs of the user ear. The individualized ear shape and its associated individualized head-related transfer function (HRTF) can be calculated from the obtained parameters based on the ear shape model and numerical acoustic simulations. Preliminary experiments, evaluating the shapes of the estimated individual ears, proved the effect of individualization.

@article{kaneko2016deepearnet:,
author={kaneko, shoken and suenaga, tsukasa and sekine, satoshi},
journal={journal of the audio engineering society},
title={deepearnet: individualizing spatial audio with photography, ear shape modeling, and neural networks},
year={2016},
volume={},
number={},
pages={},
doi={},
month={september},} @article{kaneko2016deepearnet:,
author={kaneko, shoken and suenaga, tsukasa and sekine, satoshi},
journal={journal of the audio engineering society},
title={deepearnet: individualizing spatial audio with photography, ear shape modeling, and neural networks},
year={2016},
volume={},
number={},
pages={},
doi={},
month={september},
abstract={individualizing spatial audio is of crucial importance for high-quality virtual and augmented reality audio. in this paper we propose a method for individualizing spatial audio by combining the recently proposed ear shape modeling technique with computer vision and machine learning. we use a convolutional neural network to obtain estimates of the ear shape model parameters from stereo photographs of the user ear. the individualized ear shape and its associated individualized head-related transfer function (hrtf) can be calculated from the obtained parameters based on the ear shape model and numerical acoustic simulations. preliminary experiments, evaluating the shapes of the estimated individual ears, proved the effect of individualization.},}

TY - paper
TI - DeepEarNet: Individualizing Spatial Audio with Photography, Ear Shape Modeling, and Neural Networks
SP - EP -
AU - Kaneko, Shoken
AU - Suenaga, Tsukasa
AU - Sekine, Satoshi
PY - 2016
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - September 2016 TY - paper
TI - DeepEarNet: Individualizing Spatial Audio with Photography, Ear Shape Modeling, and Neural Networks
SP - EP -
AU - Kaneko, Shoken
AU - Suenaga, Tsukasa
AU - Sekine, Satoshi
PY - 2016
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - September 2016
AB - Individualizing spatial audio is of crucial importance for high-quality virtual and augmented reality audio. In this paper we propose a method for individualizing spatial audio by combining the recently proposed ear shape modeling technique with computer vision and machine learning. We use a convolutional neural network to obtain estimates of the ear shape model parameters from stereo photographs of the user ear. The individualized ear shape and its associated individualized head-related transfer function (HRTF) can be calculated from the obtained parameters based on the ear shape model and numerical acoustic simulations. Preliminary experiments, evaluating the shapes of the estimated individual ears, proved the effect of individualization.