VCNAC: A Variable-Channel Neural Audio Codec for Mono, Stereo, and Surround Sound
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_ | 1866911389659955200 |
|---|---|
| author | Grötschla, Florian Sen, Arunasish Lombardi, Alessandro Cámbara, Guillermo Schwarz, Andreas |
| author_facet | Grötschla, Florian Sen, Arunasish Lombardi, Alessandro Cámbara, Guillermo Schwarz, Andreas |
| contents | We present VCNAC, a variable channel neural audio codec. Our approach features a single encoder and decoder parametrization that enables native inference for different channel setups, from mono speech to cinematic 5.1 channel surround audio. Channel compatibility objectives ensure that multi-channel content maintains perceptual quality when decoded to fewer channels. The shared representation enables training of generative language models on a single set of codebooks while supporting inference-time scalability across modalities and channel configurations. Evaluation using objective spatial audio metrics and subjective listening tests demonstrates that our unified approach maintains high reconstruction quality across mono, stereo, and surround audio configurations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_14960 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VCNAC: A Variable-Channel Neural Audio Codec for Mono, Stereo, and Surround Sound Grötschla, Florian Sen, Arunasish Lombardi, Alessandro Cámbara, Guillermo Schwarz, Andreas Sound Audio and Speech Processing We present VCNAC, a variable channel neural audio codec. Our approach features a single encoder and decoder parametrization that enables native inference for different channel setups, from mono speech to cinematic 5.1 channel surround audio. Channel compatibility objectives ensure that multi-channel content maintains perceptual quality when decoded to fewer channels. The shared representation enables training of generative language models on a single set of codebooks while supporting inference-time scalability across modalities and channel configurations. Evaluation using objective spatial audio metrics and subjective listening tests demonstrates that our unified approach maintains high reconstruction quality across mono, stereo, and surround audio configurations. |
| title | VCNAC: A Variable-Channel Neural Audio Codec for Mono, Stereo, and Surround Sound |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2601.14960 |