Metraipolis › archive › dc_9449f31b31bb
Metadata-Conditioned Audio Transformers for Adaptive Respiratory Sound Classification — arXiv:2611.03769
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.03769
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T12:29:28.097Z
- SHA-256 of the archived text
d57a1a5f17bb6d1f8b938fe9401956688adef756ce4590ec62074c825150f706- Stable URL of this page
https://metraipolis.com/documento/dc_9449f31b31bb
How to cite
Metadata-Conditioned Audio Transformers for Adaptive Respiratory Sound Classification — arXiv:2611.03769 — arXiv (en), https://arxiv.org/abs/2611.03769 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9449f31b31bb (Metraipolis archive dc_9449f31b31bb, sha256 d57a1a5f17bb6d1f8b938fe9401956688adef756ce4590ec62074c825150f706)
BibTeX
@misc{dc9449f31b31bb,
title = {Metadata-Conditioned Audio Transformers for Adaptive Respiratory Sound Classification — arXiv:2611.03769},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.03769},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9449f31b31bb; sha256 d57a1a5f17bb6d1f8b938fe9401956688adef756ce4590ec62074c825150f706},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03769. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Respiratory sound classification from auscultation recordings is confounded by heterogeneous acquisition conditions, including recording device, auscultation site, and patient characteristics, that introduce systematic variability unrelated to the underlying pathology. Although such metadata is often available, existing approaches either ignore it or rely on naïve fusion strategies that do not model how distinct metadata sources influence different components of the acoustic representation. We propose a family of metadata-conditioning mechanisms for the Audio Spectrogram Transformer (AST), progressing from gated residual fusion to Feature-wise Linear Modulation (FiLM) adapted to the Transformer architecture. We further introduce two novel variants: Token-Aware FiLM (TAFiLM), which applies distinct modulation to classification and patch tokens, and Soft-Factorized FiLM (SoftFiLM), which learns soft masks to align metadata factors with disentangled feature subspaces. Experiments on the ICBHI benchmark demonstrate consistent gains across all conditioning strategies. SoftFiLM achieves 64.11% on the official 4-class task (+3.94% over the baseline) and 72.40% on the 2-class task, establishing a new state-of-the-art on the 2-class task and competitive performance on the 4-class benchmark. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Sound (cs.SD) ; Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2611.03769 — 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 2026-11-04T12:26:47.223Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).