Asteroid: the PyTorch-based audio source separation toolkit for researchers

INTERSPEECH(2020)

引用 106|浏览75
暂无评分
摘要
This paper describes Asteroid, the PyTorch-based audio source separation toolkit for researchers. Inspired by the most successful neural source separation systems, it provides all neural building blocks required to build such a system. To improve reproducibility, Kaldi-style recipes on common audio source separation datasets are also provided. This paper describes the software architecture of Asteroid and its most important features. By showing experimental results obtained with Asteroid's recipes, we show that our implementations are at least on par with most results reported in reference papers. The toolkit is publicly available at https://github.com/mpariente/asteroid .
更多
查看译文
关键词
audio source separation toolkit,asteroid,pytorch-based
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要