Compression of Higher Order Ambisonics with Multichannel RVQGAN
This work addresses efficient compression of immersive audio formats for applications in virtual reality or spatial audio, but it is incremental as it extends an existing method to a multichannel context.
The authors tackled the problem of compressing third-order Ambisonics audio by proposing a multichannel extension to the RVQGAN neural coding method, achieving good quality at 16 kbps in listening tests with 7.1.4 immersive playback on the EigenScape database.
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.