Metraipolis › archive › dc_5cb92acffa80

Synthesis and editing of multi-instrument audio mixtures using scalar-quantised latents with MIDI Span conditioning — arXiv:2609.25546

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25546
License (as archived)
CC0-1.0
Archived
2026-10-08T15:08:18.128Z
SHA-256 of the archived text
23ab93a1d61300832e595a13076fe8b12613d3223c8e5688f32636a40cc37b94
Stable URL of this page
https://metraipolis.com/documento/dc_5cb92acffa80

How to cite

Synthesis and editing of multi-instrument audio mixtures using scalar-quantised latents with MIDI Span conditioning — arXiv:2609.25546 — arXiv (en), https://arxiv.org/abs/2609.25546 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5cb92acffa80 (Metraipolis archive dc_5cb92acffa80, sha256 23ab93a1d61300832e595a13076fe8b12613d3223c8e5688f32636a40cc37b94)
BibTeX
@misc{dc5cb92acffa80,
  title = {Synthesis and editing of multi-instrument audio mixtures using scalar-quantised latents with MIDI Span conditioning — arXiv:2609.25546},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25546},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5cb92acffa80; sha256 23ab93a1d61300832e595a13076fe8b12613d3223c8e5688f32636a40cc37b94},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25546. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Music creation often involves iterative refinement, changing selected musical details while retaining the rest. To support such refinement, we introduce SpanSynth-Edit, a flow-matching model for MIDI-guided synthesis and editing of multi-instrument audio mixtures using low-frame-rate scalar-quantised latents. MIDI Span encodes instrument-labelled note lifecycles as unordered event sets with continuous-valued attributes and pools each set into one conditioning vector per audio-latent frame. The model uses contextual audio for instrument-specific timbre guidance and supports editing by resynthesising the target region from revised MIDI. Experiments on single- and multi-instrument benchmarks show competitive performance and demonstrate within-frame onset control. We also discuss limitations of transcription-based note-adherence evaluation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 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/2609.25546 — 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 2026-10-08T14:37:29.537Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).