A Parametric Spatial Audio Coding Method Based on Convolutional Neural Networks

Huang Q, Wu X, Qu T. A Parametric Spatial Audio Coding Method Based on Convolutional Neural Networks. In: AES Convention 145. Audio Engineering Society; 2018. Paper 10126. Available from: https://aes.org/publications/elibrary-page/?id=19852

@inproceedings{Huang2018_19852,
  author = {Huang, Qingbo and Wu, Xihong and Qu, Tianshu},
  title = {{A Parametric Spatial Audio Coding Method Based on Convolutional Neural Networks}},
  booktitle = {AES Convention 145},
  note = {Paper 10126},
  year = {2018},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=19852}
}

TY  - CPAPER
TI  - A Parametric Spatial Audio Coding Method Based on Convolutional Neural Networks
AU  - Huang, Qingbo
AU  - Wu, Xihong
AU  - Qu, Tianshu
T2  - AES Convention 145
M1  - Paper 10126
PY  - 2018
DA  - 2018/10/06
UR  - https://aes.org/publications/elibrary-page/?id=19852
PB  - Audio Engineering Society
LA  - en
AB  - The channel based 3D audio can be compressed to a down-mix signal with side information. In this paper the inter-channel transfer functions (ITF) are estimated through training over fitting convolutional neural networks (CNN) on a specific frame. Perfectly reconstructing the original channel and keeping the spatial cues the same is set as the target of the estimation. By taking this approach, more accurate spatial cues are maintained. The subjective evaluation experiments were carried out on stereo signals to evaluate the proposed method.
ER  -