Salvato in:
| Autori principali: | , , |
|---|---|
| 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 |