Transferable Selective Virtual Sensing Active Noise Control Technique Based on Metric Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917771737038848 |
|---|---|
| author | Wang, Boxiang Shi, Dongyuan Luo, Zhengding Shen, Xiaoyi Ji, Junwei Gan, Woon-Seng |
| author_facet | Wang, Boxiang Shi, Dongyuan Luo, Zhengding Shen, Xiaoyi Ji, Junwei Gan, Woon-Seng |
| contents | Virtual sensing (VS) technology enables active noise control (ANC) systems to attenuate noise at virtual locations distant from the physical error microphones. Appropriate auxiliary filters (AF) can significantly enhance the effectiveness of VS approaches. The selection of appropriate AF for various types of noise can be automatically achieved using convolutional neural networks (CNNs). However, training the CNN model for different ANC systems is often labour-intensive and time-consuming. To tackle this problem, we propose a novel method, Transferable Selective VS, by integrating metric-learning technology into CNN-based VS approaches. The Transferable Selective VS method allows a pre-trained CNN to be applied directly to new ANC systems without requiring retraining, and it can handle unseen noise types. Numerical simulations demonstrate the effectiveness of the proposed method in attenuating sudden-varying broadband noises and real-world noises. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_05470 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Transferable Selective Virtual Sensing Active Noise Control Technique Based on Metric Learning Wang, Boxiang Shi, Dongyuan Luo, Zhengding Shen, Xiaoyi Ji, Junwei Gan, Woon-Seng Signal Processing Audio and Speech Processing Virtual sensing (VS) technology enables active noise control (ANC) systems to attenuate noise at virtual locations distant from the physical error microphones. Appropriate auxiliary filters (AF) can significantly enhance the effectiveness of VS approaches. The selection of appropriate AF for various types of noise can be automatically achieved using convolutional neural networks (CNNs). However, training the CNN model for different ANC systems is often labour-intensive and time-consuming. To tackle this problem, we propose a novel method, Transferable Selective VS, by integrating metric-learning technology into CNN-based VS approaches. The Transferable Selective VS method allows a pre-trained CNN to be applied directly to new ANC systems without requiring retraining, and it can handle unseen noise types. Numerical simulations demonstrate the effectiveness of the proposed method in attenuating sudden-varying broadband noises and real-world noises. |
| title | Transferable Selective Virtual Sensing Active Noise Control Technique Based on Metric Learning |
| topic | Signal Processing Audio and Speech Processing |
| url | https://arxiv.org/abs/2409.05470 |