English

Binaural Rendering of Ambisonic Signals by Neural Networks

Sound 2022-11-07 v1 Artificial Intelligence Audio and Speech Processing

Abstract

Binaural rendering of ambisonic signals is of broad interest to virtual reality and immersive media. Conventional methods often require manually measured Head-Related Transfer Functions (HRTFs). To address this issue, we collect a paired ambisonic-binaural dataset and propose a deep learning framework in an end-to-end manner. Experimental results show that neural networks outperform the conventional method in objective metrics and achieve comparable subjective metrics. To validate the proposed framework, we experimentally explore different settings of the input features, model structures, output features, and loss functions. Our proposed system achieves an SDR of 7.32 and MOSs of 3.83, 3.58, 3.87, 3.58 in quality, timbre, localization, and immersion dimensions.

Keywords

Cite

@article{arxiv.2211.02301,
  title  = {Binaural Rendering of Ambisonic Signals by Neural Networks},
  author = {Yin Zhu and Qiuqiang Kong and Junjie Shi and Shilei Liu and Xuzhou Ye and Ju-chiang Wang and Junping Zhang},
  journal= {arXiv preprint arXiv:2211.02301},
  year   = {2022}
}