Source Separation of Multi-source Raw Music using a Residual Quantized Variational Autoencoder

I developed a neural audio codec model based on the residual quantized variational autoencoder architecture. I train the model on the Slakh2100 dataset, a standard dataset for musical source separation, composed of multi-track audio. The model can separate audio sources, achieving almost SoTA result...

Ausführliche Beschreibung

Bibliographische Detailangaben

1. Verfasser:	Berti, Leonardo
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Learning Computer Science - Multimedia Computer Science - Sound
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!