{
  "id": 2062156,
  "title": "Finetuning Strategies for Querying Sounds by Vocal Imitation",
  "url": "https://urgent.news/2026/08/19/finetuning-strategies-for-querying-sounds-by-vocal-imitation",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-19T17:51:50.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2608.19174v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "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…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}