mlsanityData to 7 Oct 2026

Compression of Higher Order Ambisonics with Multichannel RVQGAN

arXiv 2411.12008 ↗First posted 18 Nov 2024cs.SD cs.LG cs.MMcited by 0

Not on the map. Why?

Abstract (arXiv)

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 multiple (16) channels without increasing the model bitrate. We also propose a loss function for accounting 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 scene-based, 16-channel Ambisonics content with good quality at 16 kbps when trained and tested on the EigenScape database. The model has potential applications for learning other types of content and multichannel formats.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 38 references that are in the map. First posted on arXiv 18 Nov 2024.

Builds on

13 of 38 references.

References · 13

  1. 2021SoundStream: An End-to-End Neural Audio Codeccited by 756
  2. 2022High Fidelity Neural Audio Compressioncited by 673
  3. 2023Simple and Controllable Music Generationcited by 480
  4. 2023High-Fidelity Audio Compression with Improved RVQGANcited by 423
  5. 2016A guide to convolution arithmetic for deep learningcited by 182
  6. 2024Fast Timing-Conditioned Latent Audio Diffusioncited by 178
  7. 2024Long-form music generation with latent diffusioncited by 88
  8. 2020Automatic multitrack mixing with a differentiable mixing console of neural audio effectscited by 27
  9. 2023From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusioncited by 22
  10. 2024Perceptually-motivated Spatial Audio Codec for Higher-Order Ambisonics Compressioncited by 3
  11. 2024ESC: Efficient Speech Coding with Cross-Scale Residual Vector Quantized Transformerscited by 3
  12. 2017Frequency Domain Singular Value Decomposition for Efficient Spatial Audio Codingcited by 2
1 more
  1. 2024Audio Decoding by Inverse Problem Solvingcited by 1

Built on by

Not cited yet.