Metraipolis › archive › dc_c52dcb9bb8f2
SAGE: Semantic Audio Generative Encoder — arXiv:2609.32755
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.32755
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T22:39:45.583Z
- SHA-256 of the archived text
4e410eaef92bda459c4d763e7b3c123c5e79366cc2ee1b065644cd4b2e48f8b8- Stable URL of this page
https://metraipolis.com/documento/dc_c52dcb9bb8f2
How to cite
SAGE: Semantic Audio Generative Encoder — arXiv:2609.32755 — arXiv (en), https://arxiv.org/abs/2609.32755 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c52dcb9bb8f2 (Metraipolis archive dc_c52dcb9bb8f2, sha256 4e410eaef92bda459c4d763e7b3c123c5e79366cc2ee1b065644cd4b2e48f8b8)
BibTeX
@misc{dcc52dcb9bb8f2,
title = {SAGE: Semantic Audio Generative Encoder — arXiv:2609.32755},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.32755},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c52dcb9bb8f2; sha256 4e410eaef92bda459c4d763e7b3c123c5e79366cc2ee1b065644cd4b2e48f8b8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32755. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Audio autoencoders compress waveforms into compact latent representations that serve as the interface between raw audio and downstream models. Current systems navigate a three-way trade-off between reconstruction quality, semantic structure of the latent space, and inference speed, typically favoring one or two of these at the expense of the others. This paper introduces SAGE, Semantic Audio Generative Encoder: a compact variational autoencoder, trained solely on publicly available music, that shapes its latent by distilling embeddings from a pretrained audio-text model. This 105M-parameter model runs at the inference cost of Stable Audio Open and reaches the listening-test quality of SAME-L, an autoencoder 8x larger and 4x slower, while surpassing both on objective perceptual and distributional metrics of reconstruction. Furthermore, it sets the state of the art on all nineteen probing tasks of latent semantics, in domain and out of domain. These results establish SAGE as a lightweight audio autoencoder that strikes the best balance of the three-way trade-off among those we evaluate, combining high reconstruction fidelity, state-of-the-art semantic structure, and fast inference. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG). Categorie arXiv: Sound (cs.SD) ; Machine Learning (cs.LG); Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2609.32755 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T22:14:28.637Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).