Bayesian Optimization of Deep Learning Techniques for Synthesis of Head-Related Transfer Functions

Bharitkar SG, Mauer T, Wells T, Berfanger D. Bayesian Optimization of Deep Learning Techniques for Synthesis of Head-Related Transfer Functions. In: AES Convention 146. Audio Engineering Society; 2019. Paper 10162. Available from: https://aes.org/publications/elibrary-page/?id=20295

@inproceedings{Bharitkar2019_20295,
  author = {Bharitkar, Sunil G. and Mauer, Timothy and Wells, Teresa and Berfanger, David},
  title = {{Bayesian Optimization of Deep Learning Techniques for Synthesis of Head-Related Transfer Functions}},
  booktitle = {AES Convention 146},
  note = {Paper 10162},
  year = {2019},
  month = mar,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=20295}
}

TY  - CPAPER
TI  - Bayesian Optimization of Deep Learning Techniques for Synthesis of Head-Related Transfer Functions
AU  - Bharitkar, Sunil G.
AU  - Mauer, Timothy
AU  - Wells, Teresa
AU  - Berfanger, David
T2  - AES Convention 146
M1  - Paper 10162
PY  - 2019
DA  - 2019/03/06
UR  - https://aes.org/publications/elibrary-page/?id=20295
PB  - Audio Engineering Society
LA  - en
AB  - Head-related transfer functions (HRTF) are used for creating the perception of a virtual sound source at horizontal angle ø and vertical angle ?. Publicly available databases use a subset of a full-grid of angular directions due to time and complexity to acquire and deconvolve responses. In this paper we build up on our prior research [5] by extending the technique to HRTF synthesis, using the IRCAM dataset, while reducing the computational complexity of the autoencoder (AE)+fully-connected-neural-network (FCNN) architecture by ˜ 60% using Bayesian optimization. We also present listening test results, demonstrating the performance of the presented approach, from a pilot study that was designed for assessing the directional cues of the proposed architecture.
ER  -