Parameter-Transfer Learning for Low-Resource Individualization of Head-Related Transfer Functions

Xiaoke Qi, Lu Wang


Individualized head-related transfer functions (HRTFs) play an important role in accurate localization perception. However, it is a great challenge to efficiently measure continuous HRTFs for each person in full space. In this paper, we propose a parameter-transfer learning method termed PTL to obtain individualized HRTFs based on a small set of HRTF measurements. The key idea behind PTL is to transfer a HRTF generation model from other database to a target individual. To this end, PTL first pretrains a deep neural network (DNN)-based universal model on a large database of HRTFs with the assist of domain knowledge. Domain knowledge is used to generate the input features derived from the solution to sound wave propagation equation at the physical level, and to design the loss function based on the knowledge of objective evaluation criterion. Then, the universal model is transferred to a target individual by adapting the parameters of a hidden layer of DNN with a small set of HRTF measurements. The adaptation layer is determined by experimental verification. We also conduct the objective and subjective experiments, and the results show that the proposed method outperforms the state-of-the-arts methods in terms of LSD and localization accuracy.


 DOI: 10.21437/Interspeech.2019-2558

Cite as: Qi, X., Wang, L. (2019) Parameter-Transfer Learning for Low-Resource Individualization of Head-Related Transfer Functions. Proc. Interspeech 2019, 3865-3869, DOI: 10.21437/Interspeech.2019-2558.


@inproceedings{Qi2019,
  author={Xiaoke Qi and Lu Wang},
  title={{Parameter-Transfer Learning for Low-Resource Individualization of Head-Related Transfer Functions}},
  year=2019,
  booktitle={Proc. Interspeech 2019},
  pages={3865--3869},
  doi={10.21437/Interspeech.2019-2558},
  url={http://dx.doi.org/10.21437/Interspeech.2019-2558}
}