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

Autor:	Pariente, Manuel, Cornell, Samuele, Cosentino, Joris, Sivasankaran, Sunit, Tzinis, Efthymios, Heitkaemper, Jens, Olvera, Michel, Stöter, Fabian-Robert, Hu, Mathieu, Martín-Doñas, Juan M., Ditter, David, Frank, Ariel, Deleforge, Antoine, Vincent, Emmanuel
Rok vydání:	2020
Předmět:	Electrical Engineering and Systems Science - Audio and Speech Processing Computer Science - Sound
Druh dokumentu:	Working Paper
Popis:	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 . Comment: Submitted to Interspeech 2020
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2005.04132 Zobrazit plný text záznamu View this record from Arxiv