# BLINC: Blind Calibration For Training-Free Speech Enhancement Adaptation

arXiv: https://arxiv.org/abs/2609.21898 · HTML: https://mlsanity.com/paper/2609.21898/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in Speech enhancement and noise suppression, one of 11 directions in Speech and audio language models.
- Builds on 10 of its 20 references that are in the map.
- First posted on arXiv 18 Sep 2026.

## Placed in

- Speech and audio language models / [Speech enhancement and noise suppression](https://mlsanity.com/speech/speech-enhancement-and-noise-suppression/)

## Builds on (most cited first, 10 of 10)

- [WHAM!: Extending Speech Separation to Noisy Environments](https://mlsanity.com/paper/1907.01160/) (2019)
- [ICASSP 2022 Deep Noise Suppression Challenge](https://mlsanity.com/paper/2202.13288/) (2022)
- [EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation](https://mlsanity.com/paper/2406.06185/) (2024)
- [A multi-device dataset for urban acoustic scene classification](https://mlsanity.com/paper/1807.09840/) (2018)
- [CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement](https://mlsanity.com/paper/2209.11112/) (2022)
- [RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing](https://mlsanity.com/paper/2202.08862/) (2022)
- [Test-Time Adaptation for Speech Enhancement via Domain Invariant Embedding Transformation](https://mlsanity.com/paper/2509.04280/) (2025)
- [Test-Time Adaptation For Speech Enhancement Via Mask Polarization](https://mlsanity.com/paper/2601.14770/) (2026)
- [Mitigating Over-Suppression in Speech Enhancement via Inference-Time Rethink-and-Refine Correction Module](https://mlsanity.com/paper/2608.07781/) (2026)
- [Test-time adaptation for speech enhancement with an autoregressive speech prior](https://mlsanity.com/paper/2609.03622/) (2026)

## Abstract (arXiv)

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.