FUSS
收藏arXiv2025-09-30 收录
下载链接：
http://www.jordipons.me/apps/GASS
下载链接
链接失效反馈官方服务：
资源简介：
该数据集名为FUSS，被用作训练能够分离各种任务中音频源的上游数据集。此外，在FUSS上进行微调可以提高源计数准确性和SI-SDRi，这表明模型的迁移性得到了增强。该任务的目的是实现音频源分离。
This dataset, named FUSS, serves as an upstream dataset for training models capable of audio source separation across diverse tasks. Furthermore, fine-tuning on FUSS can improve source count accuracy and SI-SDRi, indicating enhanced model transferability. The objective of this task is audio source separation.
提供机构：
Authors of the paper
