URGENT Challenge: Universality, Robustness, and Generalizability For Speech Enhancement
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929511784775680 |
|---|---|
| author | Zhang, Wangyou Scheibler, Robin Saijo, Kohei Cornell, Samuele Li, Chenda Ni, Zhaoheng Kumar, Anurag Pirklbauer, Jan Sach, Marvin Watanabe, Shinji Fingscheidt, Tim Qian, Yanmin |
| author_facet | Zhang, Wangyou Scheibler, Robin Saijo, Kohei Cornell, Samuele Li, Chenda Ni, Zhaoheng Kumar, Anurag Pirklbauer, Jan Sach, Marvin Watanabe, Shinji Fingscheidt, Tim Qian, Yanmin |
| contents | The last decade has witnessed significant advancements in deep learning-based speech enhancement (SE). However, most existing SE research has limitations on the coverage of SE sub-tasks, data diversity and amount, and evaluation metrics. To fill this gap and promote research toward universal SE, we establish a new SE challenge, named URGENT, to focus on the universality, robustness, and generalizability of SE. We aim to extend the SE definition to cover different sub-tasks to explore the limits of SE models, starting from denoising, dereverberation, bandwidth extension, and declipping. A novel framework is proposed to unify all these sub-tasks in a single model, allowing the use of all existing SE approaches. We collected public speech and noise data from different domains to construct diverse evaluation data. Finally, we discuss the insights gained from our preliminary baseline experiments based on both generative and discriminative SE methods with 12 curated metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_04660 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | URGENT Challenge: Universality, Robustness, and Generalizability For Speech Enhancement Zhang, Wangyou Scheibler, Robin Saijo, Kohei Cornell, Samuele Li, Chenda Ni, Zhaoheng Kumar, Anurag Pirklbauer, Jan Sach, Marvin Watanabe, Shinji Fingscheidt, Tim Qian, Yanmin Audio and Speech Processing Sound The last decade has witnessed significant advancements in deep learning-based speech enhancement (SE). However, most existing SE research has limitations on the coverage of SE sub-tasks, data diversity and amount, and evaluation metrics. To fill this gap and promote research toward universal SE, we establish a new SE challenge, named URGENT, to focus on the universality, robustness, and generalizability of SE. We aim to extend the SE definition to cover different sub-tasks to explore the limits of SE models, starting from denoising, dereverberation, bandwidth extension, and declipping. A novel framework is proposed to unify all these sub-tasks in a single model, allowing the use of all existing SE approaches. We collected public speech and noise data from different domains to construct diverse evaluation data. Finally, we discuss the insights gained from our preliminary baseline experiments based on both generative and discriminative SE methods with 12 curated metrics. |
| title | URGENT Challenge: Universality, Robustness, and Generalizability For Speech Enhancement |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2406.04660 |