TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909622058614784 |
|---|---|
| author | Rong, Xiaobin Wang, Dahan Hu, Qinwen Wang, Yushi Hu, Yuxiang Lu, Jing |
| author_facet | Rong, Xiaobin Wang, Dahan Hu, Qinwen Wang, Yushi Hu, Yuxiang Lu, Jing |
| contents | Universal speech enhancement aims to handle input speech with different distortions and input formats. To tackle this challenge, we present TS-URGENet, a Three-Stage Universal, Robust, and Generalizable speech Enhancement Network. To address various distortions, the proposed system employs a novel three-stage architecture consisting of a filling stage, a separation stage, and a restoration stage. The filling stage mitigates packet loss by preliminarily filling lost regions under noise interference, ensuring signal continuity. The separation stage suppresses noise, reverberation, and clipping distortion to improve speech clarity. Finally, the restoration stage compensates for bandwidth limitation, codec artifacts, and residual packet loss distortion, refining the overall speech quality. Our proposed TS-URGENet achieved outstanding performance in the Interspeech 2025 URGENT Challenge, ranking 2nd in Track 1. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_18533 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network Rong, Xiaobin Wang, Dahan Hu, Qinwen Wang, Yushi Hu, Yuxiang Lu, Jing Audio and Speech Processing Artificial Intelligence Universal speech enhancement aims to handle input speech with different distortions and input formats. To tackle this challenge, we present TS-URGENet, a Three-Stage Universal, Robust, and Generalizable speech Enhancement Network. To address various distortions, the proposed system employs a novel three-stage architecture consisting of a filling stage, a separation stage, and a restoration stage. The filling stage mitigates packet loss by preliminarily filling lost regions under noise interference, ensuring signal continuity. The separation stage suppresses noise, reverberation, and clipping distortion to improve speech clarity. Finally, the restoration stage compensates for bandwidth limitation, codec artifacts, and residual packet loss distortion, refining the overall speech quality. Our proposed TS-URGENet achieved outstanding performance in the Interspeech 2025 URGENT Challenge, ranking 2nd in Track 1. |
| title | TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network |
| topic | Audio and Speech Processing Artificial Intelligence |
| url | https://arxiv.org/abs/2505.18533 |