ImmersiveFlow: Stereo-to-7.1.4 spatial audio generation with flow matching
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914263470178304 |
|---|---|
| author | Liang, Zining Wang, Runbang Ye, Xuzhou Kong, Qiuqiang |
| author_facet | Liang, Zining Wang, Runbang Ye, Xuzhou Kong, Qiuqiang |
| contents | Immersive spatial audio has become increasingly critical for applications ranging from AR/VR to home entertainment and automotive sound systems. However, existing generative methods remain constrained to low-dimensional formats such as binaural audio and First-Order Ambisonics (FOA). Binaural rendering is inherently limited to headphone playback, while FOA suffers from spatial aliasing and insufficient resolution for high-frequency. To overcome these limitations, we introduce ImmersiveFlow, the first end-to-end generative framework that directly synthesizes discrete 7.1.4 format spatial audio from stereo input. ImmersiveFlow leverages Flow Matching to learn trajectories from stereo inputs to multichannel spatial features within a pretrained VAE latent space. At inference, the Flow Matching model predicted latent features are decoded by the VAE and converted into the final 7.1.4 waveform. Comprehensive objective and subjective evaluations demonstrate that our method produces perceptually rich sound fields and enhanced externalization, significantly outperforming traditional upmixing techniques. Code implementations and audio samples are provided at: https://github.com/violet-audio/ImmersiveFlow. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_12950 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ImmersiveFlow: Stereo-to-7.1.4 spatial audio generation with flow matching Liang, Zining Wang, Runbang Ye, Xuzhou Kong, Qiuqiang Audio and Speech Processing Immersive spatial audio has become increasingly critical for applications ranging from AR/VR to home entertainment and automotive sound systems. However, existing generative methods remain constrained to low-dimensional formats such as binaural audio and First-Order Ambisonics (FOA). Binaural rendering is inherently limited to headphone playback, while FOA suffers from spatial aliasing and insufficient resolution for high-frequency. To overcome these limitations, we introduce ImmersiveFlow, the first end-to-end generative framework that directly synthesizes discrete 7.1.4 format spatial audio from stereo input. ImmersiveFlow leverages Flow Matching to learn trajectories from stereo inputs to multichannel spatial features within a pretrained VAE latent space. At inference, the Flow Matching model predicted latent features are decoded by the VAE and converted into the final 7.1.4 waveform. Comprehensive objective and subjective evaluations demonstrate that our method produces perceptually rich sound fields and enhanced externalization, significantly outperforming traditional upmixing techniques. Code implementations and audio samples are provided at: https://github.com/violet-audio/ImmersiveFlow. |
| title | ImmersiveFlow: Stereo-to-7.1.4 spatial audio generation with flow matching |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2601.12950 |