Metraipolis › archive › dc_fdbe2f1b97fa

Synth-JEPA: Joint Embedding Prediction for Renderer-Free Synthesizer Parameter Search — arXiv:2609.31024

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.31024
License (as archived): CC0-1.0
Archived: 2026-10-08T02:19:15.756Z
SHA-256 of the archived text: ae5d2ee803be5fb817d6a986b774117b650441350e561bb40e1d6626c9cea0d5
Stable URL of this page: https://metraipolis.com/documento/dc_fdbe2f1b97fa

How to cite

Synth-JEPA: Joint Embedding Prediction for Renderer-Free Synthesizer Parameter Search — arXiv:2609.31024 — arXiv (en), https://arxiv.org/abs/2609.31024 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fdbe2f1b97fa (Metraipolis archive dc_fdbe2f1b97fa, sha256 ae5d2ee803be5fb817d6a986b774117b650441350e561bb40e1d6626c9cea0d5)

BibTeX

@misc{dcfdbe2f1b97fa,
  title = {Synth-JEPA: Joint Embedding Prediction for Renderer-Free Synthesizer Parameter Search — arXiv:2609.31024},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31024},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fdbe2f1b97fa; sha256 ae5d2ee803be5fb817d6a986b774117b650441350e561bb40e1d6626c9cea0d5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31024. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Sound matching can be formulated as optimizing synthesizer parameters against an audio-domain objective. However, objectives derived from generic audio representations are often difficult to optimize, while direct search requires rendering every candidate. We introduce Synth-JEPA, which learns mutually predictive audio and parameter representations from paired synthesizer data. At inference, candidate parameters are scored directly in this learned space, yielding a renderer-free objective whose audio geometry is shaped by parameter correspondences rather than generic audio similarity. We evaluate Synth-JEPA on Surge XT using held-out synthesizer sounds and out-of-domain NSynth and FSD50K targets, against inverse models, direct search, and learned proxy objectives. Synth-JEPA outperforms all baselines in-domain and remains competitive out-of-domain. Its matching quality continues to improve with additional test-time search, allowing compute to be traded for match quality. In pairwise listening tests, listeners preferred Synth-JEPA in 85% of trials overall. Together, these results show that an audio representation with a parameter-induced geometry allows synthesizer sound matching to be approached as an effective renderer-free search problem.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 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/2609.31024 — 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 2026-10-08T01:43:06.804Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).