Source Separation of Multi-source Raw Music using a Residual Quantized Variational Autoencoder
Sound
2024-08-14 v1 Machine Learning
Multimedia
Audio and Speech Processing
Abstract
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 results with much less computing power. The code is publicly available at github.com/LeonardoBerti00/Source-Separation-of-Multi-source-Music-using-Residual-Quantizad-Variational-Autoencoder
Keywords
Cite
@article{arxiv.2408.07020,
title = {Source Separation of Multi-source Raw Music using a Residual Quantized Variational Autoencoder},
author = {Leonardo Berti},
journal= {arXiv preprint arXiv:2408.07020},
year = {2024}
}
Comments
9 pages