cunetControl mechanisms to the U-Net architecture for doing multiple source separation instruments
TasNetA PyTorch implementation of Time-domain Audio Separation Network (TasNet) with Permutation Invariant Training (PIT) for speech separation.
AMSS-NetA PyTorch implementation of the paper: "AMSS-Net: Audio Manipulation on User-Specified Sources with Textual Queries" (ACM Multimedia 2021)
DeepSeparationKeras Implementation and Experiments with Deep Recurrent Neural Networks for Source Separation
rl singing voiceUnsupervised Representation Learning for Singing Voice Separation
soundscape IRTools of soundscape information retrieval, this repository is a developing project. Please go to https://github.com/meil-brcas-org/soundscape_IR for full releases.
wavenetAudio source separation (mixture to vocal) using the Wavenet
SpleeterRTReal time monaural source separation base on fully convolutional neural network operates on Time-frequency domain.