Salvato in:
Dettagli Bibliografici
Autori principali: Raichle, Tobias, Amini, Erfan, Yang, Bin
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2601.14770
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916014984265728
author Raichle, Tobias
Amini, Erfan
Yang, Bin
author_facet Raichle, Tobias
Amini, Erfan
Yang, Bin
contents Adapting speech enhancement (SE) models to unseen environments is crucial for practical deployments, yet test-time adaptation (TTA) for SE remains largely under-explored due to a lack of understanding of how SE models degrade under domain shifts. We observe that mask-based SE models lose confidence under domain shifts, with predicted masks becoming flattened and losing decisive speech preservation and noise suppression. Based on this insight, we propose mask polarization (MPol), a lightweight TTA method that restores mask bimodality through distribution comparison using the Wasserstein distance. MPol requires no additional parameters beyond the trained model, making it suitable for resource-constrained edge deployments. Experimental results across diverse domain shifts and architectures demonstrate that MPol achieves very consistent gains that are competitive with significantly more complex approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2601_14770
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Test-Time Adaptation For Speech Enhancement Via Mask Polarization
Raichle, Tobias
Amini, Erfan
Yang, Bin
Audio and Speech Processing
Adapting speech enhancement (SE) models to unseen environments is crucial for practical deployments, yet test-time adaptation (TTA) for SE remains largely under-explored due to a lack of understanding of how SE models degrade under domain shifts. We observe that mask-based SE models lose confidence under domain shifts, with predicted masks becoming flattened and losing decisive speech preservation and noise suppression. Based on this insight, we propose mask polarization (MPol), a lightweight TTA method that restores mask bimodality through distribution comparison using the Wasserstein distance. MPol requires no additional parameters beyond the trained model, making it suitable for resource-constrained edge deployments. Experimental results across diverse domain shifts and architectures demonstrate that MPol achieves very consistent gains that are competitive with significantly more complex approaches.
title Test-Time Adaptation For Speech Enhancement Via Mask Polarization
topic Audio and Speech Processing
url https://arxiv.org/abs/2601.14770