{
  "id": 910,
  "url": "https://arxiv.org/abs/2606.23712v1",
  "title": "Audio-visual Contrastive Alignment for Diffusion-based Visual-conditioned Speech Enhancement",
  "summary": "Audio-visual speech enhancement (AVSE) exploits visual cues such as lip movements to recover speech in noisy environments. Recent work introduced diffusion-based unsupervised AVSE, where a speech diffusion model conditioned on visual features via cross-attention is trained and used as a data-driven prior for posterior sampling-based speech enhancement. Despite promising performance over its audio-only counterpart, the impact of explicitly enforcing cross-modal alignment in the fusion remains unc",
  "authors": "Colombe Mboungou, Mostafa Sadeghi, Jean-Eudes Ayilo, Romain Serizel",
  "category": "research",
  "topics": "safety-alignment,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-06-16T06:39:04.000Z",
  "fetched_at": "2026-07-14T14:14:54.531Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/910",
  "original_url": "https://arxiv.org/abs/2606.23712v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}