Metraipolis › archive › dc_ef90d4099386
BLINC: Blind Calibration For Training-Free Speech Enhancement Adaptation — arXiv:2609.21898
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.21898
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T03:12:18.353Z
- SHA-256 of the archived text
5138a7b0593d99d948bc165ec3b3fd2556782ee7941fcf007c42de3cd94ba3ad- Stable URL of this page
https://metraipolis.com/documento/dc_ef90d4099386
How to cite
BLINC: Blind Calibration For Training-Free Speech Enhancement Adaptation — arXiv:2609.21898 — arXiv (en), https://arxiv.org/abs/2609.21898 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ef90d4099386 (Metraipolis archive dc_ef90d4099386, sha256 5138a7b0593d99d948bc165ec3b3fd2556782ee7941fcf007c42de3cd94ba3ad)
BibTeX
@misc{dcef90d4099386,
title = {BLINC: Blind Calibration For Training-Free Speech Enhancement Adaptation — arXiv:2609.21898},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.21898},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ef90d4099386; sha256 5138a7b0593d99d948bc165ec3b3fd2556782ee7941fcf007c42de3cd94ba3ad},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21898. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Speech enhancement (SE) models degrade under domain shifts and have to adapt to unseen target domains during deployment. Most existing test-time adaptation (TTA) methods for SE do so by adapting a subset of the model weights using a self-supervised loss, which requires backpropagation at test-time and permanently alters the model. We instead recalibrate the prediction itself and propose BLINC, a training-free TTA method that remaps the predicted time-frequency mask onto a bimodal target distribution by histogram matching. At test-time, the target distribution is parameterized from blind features of the noisy recording, so neither a reference distribution from a classical algorithm nor online metric optimization is involved. BLINC improves the overall quality of both evaluated SE models on almost every target condition and matches or exceeds the loss-based TTA baselines at minimal overhead. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in eess.AS). Categorie arXiv: Audio and Speech Processing (eess.AS) ; Sound (cs.SD). Pagina del lavoro: https://arxiv.org/abs/2609.21898 — 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 2026-10-10T03:01:34.418Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).