Towards Lightweight Adaptation of Speech Enhancement Models in Real-World Environments
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910045190488064 |
|---|---|
| author | Cheng, Longbiao Liu, Shih-Chii |
| author_facet | Cheng, Longbiao Liu, Shih-Chii |
| contents | Recent studies have shown that post-deployment adaptation can improve the robustness of speech enhancement models in unseen noise conditions. However, existing methods often incur prohibitive computational and memory costs, limiting their suitability for on-device deployment. In this work, we investigate model adaptation in realistic settings with dynamic acoustic scene changes and propose a lightweight framework that augments a frozen backbone with low-rank adapters updated via self-supervised training. Experiments on sequential scene evaluations spanning 111 environments across 37 noise types and three signal-to-noise ratio ranges, including the challenging [-8, 0] dB range, show that our method updates fewer than 1% of the base model's parameters while achieving an average 1.51 dB SI-SDR improvement within only 20 updates per scene. Compared to state-of-the-art approaches, our framework achieves competitive or superior perceptual quality with smoother and more stable convergence, demonstrating its practicality for lightweight on-device adaptation of speech enhancement models under real-world acoustic conditions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07471 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Towards Lightweight Adaptation of Speech Enhancement Models in Real-World Environments Cheng, Longbiao Liu, Shih-Chii Audio and Speech Processing Artificial Intelligence Machine Learning Sound Recent studies have shown that post-deployment adaptation can improve the robustness of speech enhancement models in unseen noise conditions. However, existing methods often incur prohibitive computational and memory costs, limiting their suitability for on-device deployment. In this work, we investigate model adaptation in realistic settings with dynamic acoustic scene changes and propose a lightweight framework that augments a frozen backbone with low-rank adapters updated via self-supervised training. Experiments on sequential scene evaluations spanning 111 environments across 37 noise types and three signal-to-noise ratio ranges, including the challenging [-8, 0] dB range, show that our method updates fewer than 1% of the base model's parameters while achieving an average 1.51 dB SI-SDR improvement within only 20 updates per scene. Compared to state-of-the-art approaches, our framework achieves competitive or superior perceptual quality with smoother and more stable convergence, demonstrating its practicality for lightweight on-device adaptation of speech enhancement models under real-world acoustic conditions. |
| title | Towards Lightweight Adaptation of Speech Enhancement Models in Real-World Environments |
| topic | Audio and Speech Processing Artificial Intelligence Machine Learning Sound |
| url | https://arxiv.org/abs/2603.07471 |