Metraipolis › archive › dc_bbd3438fe4fb

ROAM-ASD: Robust Open-World Active Speaker Detection with Flexible Multimodal Fusion — arXiv:2609.26648

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.26648
License (as archived): CC0-1.0
Archived: 2026-10-08T16:43:11.507Z
SHA-256 of the archived text: a1a62796e1678e0082a8bb1e618bf3138eae42a979fc2fd451c6ba5fb99608c3
Stable URL of this page: https://metraipolis.com/documento/dc_bbd3438fe4fb

How to cite

ROAM-ASD: Robust Open-World Active Speaker Detection with Flexible Multimodal Fusion — arXiv:2609.26648 — arXiv (en), https://arxiv.org/abs/2609.26648 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bbd3438fe4fb (Metraipolis archive dc_bbd3438fe4fb, sha256 a1a62796e1678e0082a8bb1e618bf3138eae42a979fc2fd451c6ba5fb99608c3)

BibTeX

@misc{dcbbd3438fe4fb,
  title = {ROAM-ASD: Robust Open-World Active Speaker Detection with Flexible Multimodal Fusion — arXiv:2609.26648},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26648},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bbd3438fe4fb; sha256 a1a62796e1678e0082a8bb1e618bf3138eae42a979fc2fd451c6ba5fb99608c3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26648. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Active speaker detection (ASD) requires reliable association between visible faces and acoustic speech, yet existing systems often degrade under challenging domains or incomplete observations. We introduce ROAM-ASD, a robust audiovisual framework that jointly models audio, full-face, and fine-grained mouth representations. A unified joint self-attention mechanism processes all input streams together with modality-agnostic query tokens, enabling direct interaction among available modality inputs. Modality dropout further improves robustness when input streams are unavailable. ROAM-ASD achieves state-of-the-art performance across five ASD benchmarks: 98.8% mAP on WASD, 87.9% on UniTalk, 96.5% on AVA, 99.3% on ASW, and 98.2% on Talkies, improving over previous best systems by 5.1, 4.7, 0.9, 1.0, and 2.1 mAP points, respectively. ROAM-ASD also substantially improves zero-shot cross-dataset generalization and remains robust to missing observations.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-23 in cs.CV).
Categorie arXiv: Multimedia (cs.MM) ; Computer Vision and Pattern Recognition (cs.CV); Sound (cs.SD); Audio and Speech Processing (eess.AS); Image and Video Processing (eess.IV).
Pagina del lavoro: https://arxiv.org/abs/2609.26648 — 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 2026-10-08T15:56:18.251Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).