{
  "abstract": "Passive acoustic monitoring enables large-scale wildlife observation. Most bioacoustic classifiers predict species presence in a time window without localizing vocalizations precisely in time or frequency, limiting downstream analyses. We formulate time-frequency localization of bird calls as object detection on spectrograms and compare three computer vision model families (YOLO11, SAM 3, RF-DETR) against a non-learnable baseline. We introduce Intersection over Minimum (IoMin), an evaluation metric that better handles ambiguous acoustic boundaries than IoU. We also open-source a browser-based tool for efficient bounding-box labeling. The best RF-DETR model nearly doubles baseline performance on in-distribution, dense soundscapes from Singapore (83.4% vs. 42.1% IoMin@50 F1-score) and generalizes better to out-of-distribution recordings from Hawaii (63.2% vs. 48.6%). These results indicate that fine-tuned computer-vision models are well suited for time-frequency localization of bird vocalizations in complex soundscapes.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2606.10407",
  "author_total": 4,
  "authors": [
    {
      "name": "Simen Hexeberg"
    },
    {
      "name": "Fanghui Tong"
    },
    {
      "name": "Hari Vishnu"
    },
    {
      "name": "Mandar Chitre"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/28rq8ebhasdm9.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2606.10407",
  "fulltext_url": null,
  "id": "28rq8ebhasdm9",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2606.10407",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.CV"
    ],
    [
      "arxiv",
      "cs.SD"
    ],
    [
      "arxiv",
      "q-bio.QM"
    ],
    [
      "openalex",
      "1711|Music and Audio Processing"
    ]
  ],
  "openalex": "W7164125880",
  "pdf_url": "https://arxiv.org/pdf/2606.10407",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-28",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/28rq8ebhasdm9.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:25:21Z",
      "native_id": "2606.10407",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2606.10407"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.QM",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Time-frequency localization of bird calls in dense soundscapes",
  "title_text": "Time-frequency localization of bird calls in dense soundscapes",
  "type": "preprint",
  "updated_at": "2026-10-30T12:25:21Z",
  "url": "https://research.draconitic.com/paper/28rq8ebhasdm9",
  "venue": "arXiv",
  "versions": []
}