Interspeech 2025 URGENT Speech Enhancement Challenge
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_ | 1866918042657619968 |
|---|---|
| author | Saijo, Kohei Zhang, Wangyou Cornell, Samuele Scheibler, Robin Li, Chenda Ni, Zhaoheng Kumar, Anurag Sach, Marvin Fu, Yihui Wang, Wei Fingscheidt, Tim Watanabe, Shinji |
| author_facet | Saijo, Kohei Zhang, Wangyou Cornell, Samuele Scheibler, Robin Li, Chenda Ni, Zhaoheng Kumar, Anurag Sach, Marvin Fu, Yihui Wang, Wei Fingscheidt, Tim Watanabe, Shinji |
| contents | There has been a growing effort to develop universal speech enhancement (SE) to handle inputs with various speech distortions and recording conditions. The URGENT Challenge series aims to foster such universal SE by embracing a broad range of distortion types, increasing data diversity, and incorporating extensive evaluation metrics. This work introduces the Interspeech 2025 URGENT Challenge, the second edition of the series, to explore several aspects that have received limited attention so far: language dependency, universality for more distortion types, data scalability, and the effectiveness of using noisy training data. We received 32 submissions, where the best system uses a discriminative model, while most other competitive ones are hybrid methods. Analysis reveals some key findings: (i) some generative or hybrid approaches are preferred in subjective evaluations over the top discriminative model, and (ii) purely generative SE models can exhibit language dependency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_23212 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Interspeech 2025 URGENT Speech Enhancement Challenge Saijo, Kohei Zhang, Wangyou Cornell, Samuele Scheibler, Robin Li, Chenda Ni, Zhaoheng Kumar, Anurag Sach, Marvin Fu, Yihui Wang, Wei Fingscheidt, Tim Watanabe, Shinji Audio and Speech Processing There has been a growing effort to develop universal speech enhancement (SE) to handle inputs with various speech distortions and recording conditions. The URGENT Challenge series aims to foster such universal SE by embracing a broad range of distortion types, increasing data diversity, and incorporating extensive evaluation metrics. This work introduces the Interspeech 2025 URGENT Challenge, the second edition of the series, to explore several aspects that have received limited attention so far: language dependency, universality for more distortion types, data scalability, and the effectiveness of using noisy training data. We received 32 submissions, where the best system uses a discriminative model, while most other competitive ones are hybrid methods. Analysis reveals some key findings: (i) some generative or hybrid approaches are preferred in subjective evaluations over the top discriminative model, and (ii) purely generative SE models can exhibit language dependency. |
| title | Interspeech 2025 URGENT Speech Enhancement Challenge |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2505.23212 |