Top 11 source-separation open source projects

Singing-Voice Separation From Monaural Recordings Using Deep Recurrent Neural Networks

Control mechanisms to the U-Net architecture for doing multiple source separation instruments

A PyTorch implementation of Time-domain Audio Separation Network (TasNet) with Permutation Invariant Training (PIT) for speech separation.

A PyTorch implementation of the paper: "AMSS-Net: Audio Manipulation on User-Specified Sources with Textual Queries" (ACM Multimedia 2021)

Keras Implementation and Experiments with Deep Recurrent Neural Networks for Source Separation

Unsupervised Representation Learning for Singing Voice Separation

target speaker extraction and verification for multi-talker speech

An implementation of audio source separation tools.

Tools of soundscape information retrieval, this repository is a developing project. Please go to https://github.com/meil-brcas-org/soundscape_IR for full releases.

Audio source separation (mixture to vocal) using the Wavenet

Real time monaural source separation base on fully convolutional neural network operates on Time-frequency domain.