Metraipolis › archive › dc_2ee8d3224065

Zero-Shot Respiratory Sound Classification through LLM-Augmented Audio-Text Alignment — arXiv:2609.00055

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.00055
License (as archived)
CC0-1.0
Archived
2026-10-17T06:32:37.277Z
SHA-256 of the archived text
da3d7593ad9689d6a1f50cf2ea0890ec249f914e425a1d0a85a3327f7eee51a7
Stable URL of this page
https://metraipolis.com/documento/dc_2ee8d3224065

How to cite

Zero-Shot Respiratory Sound Classification through LLM-Augmented Audio-Text Alignment — arXiv:2609.00055 — arXiv (en), https://arxiv.org/abs/2609.00055 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2ee8d3224065 (Metraipolis archive dc_2ee8d3224065, sha256 da3d7593ad9689d6a1f50cf2ea0890ec249f914e425a1d0a85a3327f7eee51a7)
BibTeX
@misc{dc2ee8d3224065,
  title = {Zero-Shot Respiratory Sound Classification through LLM-Augmented Audio-Text Alignment — arXiv:2609.00055},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00055},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2ee8d3224065; sha256 da3d7593ad9689d6a1f50cf2ea0890ec249f914e425a1d0a85a3327f7eee51a7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00055. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Self-supervised respiratory encoders lack semantic grounding in clinical domain needed for zero-shot inference, limiting their utility without task-specific labeled data. We propose a framework that aligns these encoders with medical terminology in a shared latent space turning them into a zero-shot-capable foundation model. To address paired data scarcity, we use a medical LLM to synthesize structured reports from metadata, creating dense semantic anchors for contrastive learning. Our training combines a sigmoid-based contrastive loss with encoder's native SSL objective and similarity-aware negative sampling to sharpen pathological boundaries. Across 9 tasks on 6 datasets, our method achieves a 61.3% mean zero-shot AUC, surpassing CLAP (51.4%) and Qwen2-Audio (54.9%) while reaching the highest linear probing AUC (71.6%) with only 43% of data used by full-scale baselines, showing that structured semantic alignment outperforms large-scale, general-purpose models in clinical diagnostics.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Sound (cs.SD).
Pagina del lavoro: https://arxiv.org/abs/2609.00055 — 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 2026-10-17T06:15:12.719Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).