Vision Transformer Segmentation for Visual Bird Sound Denoising
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917692944941056 |
|---|---|
| author | Kumar, Sahil Li, Jialu Zhang, Youshan |
| author_facet | Kumar, Sahil Li, Jialu Zhang, Youshan |
| contents | Audio denoising, especially in the context of bird sounds, remains a challenging task due to persistent residual noise. Traditional and deep learning methods often struggle with artificial or low-frequency noise. In this work, we propose ViTVS, a novel approach that leverages the power of the vision transformer (ViT) architecture. ViTVS adeptly combines segmentation techniques to disentangle clean audio from complex signal mixtures. Our key contributions encompass the development of ViTVS, introducing comprehensive, long-range, and multi-scale representations. These contributions directly tackle the limitations inherent in conventional approaches. Extensive experiments demonstrate that ViTVS outperforms state-of-the-art methods, positioning it as a benchmark solution for real-world bird sound denoising applications. Source code is available at: https://github.com/aiai-4/ViVTS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_09167 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Vision Transformer Segmentation for Visual Bird Sound Denoising Kumar, Sahil Li, Jialu Zhang, Youshan Sound Audio and Speech Processing Audio denoising, especially in the context of bird sounds, remains a challenging task due to persistent residual noise. Traditional and deep learning methods often struggle with artificial or low-frequency noise. In this work, we propose ViTVS, a novel approach that leverages the power of the vision transformer (ViT) architecture. ViTVS adeptly combines segmentation techniques to disentangle clean audio from complex signal mixtures. Our key contributions encompass the development of ViTVS, introducing comprehensive, long-range, and multi-scale representations. These contributions directly tackle the limitations inherent in conventional approaches. Extensive experiments demonstrate that ViTVS outperforms state-of-the-art methods, positioning it as a benchmark solution for real-world bird sound denoising applications. Source code is available at: https://github.com/aiai-4/ViVTS. |
| title | Vision Transformer Segmentation for Visual Bird Sound Denoising |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2406.09167 |