SpectroStream: A Versatile Neural Codec for General Audio

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Yunpeng, Han, Kehang, McWilliams, Brian, Borsos, Zalan, Tagliasacchi, Marco
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909727316770816
author Li, Yunpeng
Han, Kehang
McWilliams, Brian
Borsos, Zalan
Tagliasacchi, Marco
author_facet Li, Yunpeng
Han, Kehang
McWilliams, Brian
Borsos, Zalan
Tagliasacchi, Marco
contents We propose SpectroStream, a full-band multi-channel neural audio codec. Successor to the well-established SoundStream, SpectroStream extends its capability beyond 24 kHz monophonic audio and enables high-quality reconstruction of 48 kHz stereo music at bit rates of 4--16 kbps. This is accomplished with a new neural architecture that leverages audio representation in the time-frequency domain, which leads to better audio quality especially at higher sample rate. The model also uses a delayed-fusion strategy to handle multi-channel audio, which is crucial in balancing per-channel acoustic quality and cross-channel phase consistency.
format Preprint
id arxiv_https___arxiv_org_abs_2508_05207
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SpectroStream: A Versatile Neural Codec for General Audio
Li, Yunpeng
Han, Kehang
McWilliams, Brian
Borsos, Zalan
Tagliasacchi, Marco
Sound
Artificial Intelligence
Audio and Speech Processing
We propose SpectroStream, a full-band multi-channel neural audio codec. Successor to the well-established SoundStream, SpectroStream extends its capability beyond 24 kHz monophonic audio and enables high-quality reconstruction of 48 kHz stereo music at bit rates of 4--16 kbps. This is accomplished with a new neural architecture that leverages audio representation in the time-frequency domain, which leads to better audio quality especially at higher sample rate. The model also uses a delayed-fusion strategy to handle multi-channel audio, which is crucial in balancing per-channel acoustic quality and cross-channel phase consistency.
title SpectroStream: A Versatile Neural Codec for General Audio
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2508.05207