Source Separation of Multi-source Raw Music using a Residual Quantized Variational Autoencoder
This work addresses source separation for music processing, offering a more efficient solution that could benefit audio editing and production applications, though it appears incremental in nature.
The paper tackles the problem of separating multiple audio sources in raw music using a residual quantized variational autoencoder, achieving near state-of-the-art results with significantly reduced computational requirements.
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