Compression of Higher Order Ambisonics with Multichannel RVQGAN

Hirvonen T, Namazi M. Compression of Higher Order Ambisonics with Multichannel RVQGAN. In: 2025 AES International Conference on Artificial Intelligence and Machine Learning for Audio. Audio Engineering Society; 2025. Paper 3. Available from: https://aes.org/publications/elibrary-page/?id=22992

@inproceedings{Hirvonen2025_22992,
  author = {Hirvonen, Toni and Namazi, Mahmoud},
  title = {{Compression of Higher Order Ambisonics with Multichannel RVQGAN}},
  booktitle = {2025 AES International Conference on Artificial Intelligence and Machine Learning for Audio},
  note = {Paper 3},
  year = {2025},
  month = sep,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=22992}
}

TY  - CPAPER
TI  - Compression of Higher Order Ambisonics with Multichannel RVQGAN
AU  - Hirvonen, Toni
AU  - Namazi, Mahmoud
T2  - 2025 AES International Conference on Artificial Intelligence and Machine Learning for Audio
M1  - Paper 3
PY  - 2025
DA  - 2025/09/02
UR  - https://aes.org/publications/elibrary-page/?id=22992
PB  - Audio Engineering Society
LA  - en
AB  - A multichannel extension to the RVQGAN neural coding method is proposed, and realized for data-driven compression of third-order Ambisonics audio. The input- and output layers of the generator and discriminator models are modified to accept multichannel input. We also propose a loss function which accounts for spatial perception in immersive reproduction, and transfer learning from single-channel models. Listening test results with 7.1.4 immersive playback show that the proposed extension is suitable for coding ambient scene-based, third-order (16-channel) Ambisonics content with good quality at 16 kbps when trained and tested on the EigenScape database. The model presented is the first neural codec dedicated to immersive audio to the authors knowledge and has potential applications for learning other types of content and multichannel formats.
ER  -