RaD-Net: A Repairing and Denoising Network for Speech Signal Improvement
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_ | 1866911751596933120 |
|---|---|
| author | Liu, Mingshuai Chen, Zhuangqi Yan, Xiaopeng Lv, Yuanjun Xia, Xianjun Huang, Chuanzeng Xiao, Yijian Xie, Lei |
| author_facet | Liu, Mingshuai Chen, Zhuangqi Yan, Xiaopeng Lv, Yuanjun Xia, Xianjun Huang, Chuanzeng Xiao, Yijian Xie, Lei |
| contents | This paper introduces our repairing and denoising network (RaD-Net) for the ICASSP 2024 Speech Signal Improvement (SSI) Challenge. We extend our previous framework based on a two-stage network and propose an upgraded model. Specifically, we replace the repairing network with COM-Net from TEA-PSE. In addition, multi-resolution discriminators and multi-band discriminators are adopted in the training stage. Finally, we use a three-step training strategy to optimize our model. We submit two models with different sets of parameters to meet the RTF requirement of the two tracks. According to the official results, the proposed systems rank 2nd in track 1 and 3rd in track 2. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_04389 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RaD-Net: A Repairing and Denoising Network for Speech Signal Improvement Liu, Mingshuai Chen, Zhuangqi Yan, Xiaopeng Lv, Yuanjun Xia, Xianjun Huang, Chuanzeng Xiao, Yijian Xie, Lei Sound Audio and Speech Processing This paper introduces our repairing and denoising network (RaD-Net) for the ICASSP 2024 Speech Signal Improvement (SSI) Challenge. We extend our previous framework based on a two-stage network and propose an upgraded model. Specifically, we replace the repairing network with COM-Net from TEA-PSE. In addition, multi-resolution discriminators and multi-band discriminators are adopted in the training stage. Finally, we use a three-step training strategy to optimize our model. We submit two models with different sets of parameters to meet the RTF requirement of the two tracks. According to the official results, the proposed systems rank 2nd in track 1 and 3rd in track 2. |
| title | RaD-Net: A Repairing and Denoising Network for Speech Signal Improvement |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2401.04389 |