Metraipolis › archive › dc_f42f5bc77acc

Finetuning Strategies for Querying Sounds by Vocal Imitation — arXiv:2608.19174

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.19174
License (as archived)
CC0-1.0
Archived
2026-10-18T13:45:37.982Z
SHA-256 of the archived text
299db2ca123a2a823d464cd7c77df83d324eab561c20b00fda7c8968445f91bc
Stable URL of this page
https://metraipolis.com/documento/dc_f42f5bc77acc

How to cite

Finetuning Strategies for Querying Sounds by Vocal Imitation — arXiv:2608.19174 — arXiv (en), https://arxiv.org/abs/2608.19174 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f42f5bc77acc (Metraipolis archive dc_f42f5bc77acc, sha256 299db2ca123a2a823d464cd7c77df83d324eab561c20b00fda7c8968445f91bc)
BibTeX
@misc{dcf42f5bc77acc,
  title = {Finetuning Strategies for Querying Sounds by Vocal Imitation — arXiv:2608.19174},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.19174},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f42f5bc77acc; sha256 299db2ca123a2a823d464cd7c77df83d324eab561c20b00fda7c8968445f91bc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19174. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This technical report describes our winning submission to the AES AIMLA 2025 Challenge on querying sound effects by vocal imitation. We investigate two complementary fine-tuning strategies: contrastive learning with a frozen, pretrained CED encoder, and joint contrastive-triplet learning with semi-hard negatives using a MobileNetV3 encoder. This report has been updated for posterity to include details released after the challenge.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-20 in cs.AI).
Categorie arXiv: Sound (cs.SD) ; Artificial Intelligence (cs.AI); Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2608.19174 — 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 2026-10-18T13:41:18.007Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).