Deep generative fixed-filter active noise control
Due to the slow convergence and poor tracking ability, conventional LMS-based adaptive algorithms are less capable of handling dynamic noises. Selective fixed-filter active noise control (SFANC) can significantly reduce response time by selecting appropriate pre-trained control filters for different...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/169105 |
| _version_ | 1826119529645735936 |
|---|---|
| author | Luo, Zhengding Shi, Dongyuan Shen, Xiaoyi Ji, Junwei Gan, Woon-Seng |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Luo, Zhengding Shi, Dongyuan Shen, Xiaoyi Ji, Junwei Gan, Woon-Seng |
| author_sort | Luo, Zhengding |
| collection | NTU |
| description | Due to the slow convergence and poor tracking ability, conventional LMS-based adaptive algorithms are less capable of handling dynamic noises. Selective fixed-filter active noise control (SFANC) can significantly reduce response time by selecting appropriate pre-trained control filters for different noises. Nonetheless, the limited number of pre-trained control filters may affect noise reduction performance, especially when the incoming noise differs much from the initial noises during pre-training. Therefore, a generative fixed-filter active noise control (GFANC) method is proposed in this paper to overcome the limitation. Based on deep learning and a perfect-reconstruction filter bank, the GFANC method only
requires a few prior data (one pre-trained broadband control filter) to automatically generate suitable control filters for various noises. The efficacy of the GFANC method is demonstrated by numerical simulations on real-recorded noises. |
| first_indexed | 2024-10-01T05:01:51Z |
| format | Conference Paper |
| id | ntu-10356/169105 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:01:51Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1691052023-07-07T15:38:37Z Deep generative fixed-filter active noise control Luo, Zhengding Shi, Dongyuan Shen, Xiaoyi Ji, Junwei Gan, Woon-Seng School of Electrical and Electronic Engineering 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023) Science::Physics::Acoustics Active Noise Control Deep Learning Due to the slow convergence and poor tracking ability, conventional LMS-based adaptive algorithms are less capable of handling dynamic noises. Selective fixed-filter active noise control (SFANC) can significantly reduce response time by selecting appropriate pre-trained control filters for different noises. Nonetheless, the limited number of pre-trained control filters may affect noise reduction performance, especially when the incoming noise differs much from the initial noises during pre-training. Therefore, a generative fixed-filter active noise control (GFANC) method is proposed in this paper to overcome the limitation. Based on deep learning and a perfect-reconstruction filter bank, the GFANC method only requires a few prior data (one pre-trained broadband control filter) to automatically generate suitable control filters for various noises. The efficacy of the GFANC method is demonstrated by numerical simulations on real-recorded noises. Submitted/Accepted version 2023-07-05T05:43:13Z 2023-07-05T05:43:13Z 2023 Conference Paper Luo, Z., Shi, D., Shen, X., Ji, J. & Gan, W. (2023). Deep generative fixed-filter active noise control. 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023). https://dx.doi.org/10.1109/ICASSP49357.2023.10095205 978-1-7281-6327-7 https://hdl.handle.net/10356/169105 10.1109/ICASSP49357.2023.10095205 en © 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/ICASSP49357.2023.10095205. application/pdf |
| spellingShingle | Science::Physics::Acoustics Active Noise Control Deep Learning Luo, Zhengding Shi, Dongyuan Shen, Xiaoyi Ji, Junwei Gan, Woon-Seng Deep generative fixed-filter active noise control |
| title | Deep generative fixed-filter active noise control |
| title_full | Deep generative fixed-filter active noise control |
| title_fullStr | Deep generative fixed-filter active noise control |
| title_full_unstemmed | Deep generative fixed-filter active noise control |
| title_short | Deep generative fixed-filter active noise control |
| title_sort | deep generative fixed filter active noise control |
| topic | Science::Physics::Acoustics Active Noise Control Deep Learning |
| url | https://hdl.handle.net/10356/169105 |
| work_keys_str_mv | AT luozhengding deepgenerativefixedfilteractivenoisecontrol AT shidongyuan deepgenerativefixedfilteractivenoisecontrol AT shenxiaoyi deepgenerativefixedfilteractivenoisecontrol AT jijunwei deepgenerativefixedfilteractivenoisecontrol AT ganwoonseng deepgenerativefixedfilteractivenoisecontrol |