There are 31 repositories under source-separation topic.
Isolate vocals, drums, bass, and other instrumental stems from any song
Windows desktop front end for Spleeter - AI source separation
The PyTorch-based audio source separation toolkit for researchers
Unofficial PyTorch implementation of Google AI's VoiceFilter system
A curated list of different papers and datasets in various areas of audio-visual processing
A PyTorch implementation of Conv-TasNet described in "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation" with Permutation Invariant Training (PIT).
Deep Xi: A deep learning approach to a priori SNR estimation implemented in TensorFlow 2/Keras. For speech enhancement and robust ASR.
Self-hostable web app for isolating the vocal, accompaniment, bass, and drums of any song. Supports Spleeter, D3Net, Demucs, Tasnet, X-UMX. Built with React and Django.
Deep Convolutional Neural Networks for Musical Source Separation
This repository contains audio samples and supplementary materials accompanying publications by the "Speaker, Voice and Language" team at Google.
Cross-platform speech toolset, used from the command-line or as a Node.js library. Includes a variety of engines for speech synthesis, speech recognition, forced alignment, speech translation, voice isolation, language detection and more.
Tutorial covering Open Source tools for Source Separation.
Deep Recurrent Neural Networks for Source Separation
example free website for client-side music demixing with Demucs + WebAssembly
Deep learning based speech source separation using Pytorch
A PyTorch implementation of DNN-based source separation.
Windows desktop front end for Spleeter - AI source separation - A fork of: https://github.com/boy1dr/SpleeterGui
A neural network for end-to-end music source separation
KUIELAB-MDX-Net got the 2nd place on the Leaderboard A and the 3rd place on the Leaderboard B in the MDX-Challenge ISMIR 2021
Speech Enhancement based on DNN (Spectral-Mapping, TF-Masking), DNN-NMF, NMF
target speaker extraction and verification for multi-talker speech
Unofficial PyTorch implementation of Music Source Separation with Band-split RNN
Real time monaural source separation base on fully convolutional neural network operates on Time-frequency domain.
A PyTorch implementation of Time-domain Audio Separation Network (TasNet) with Permutation Invariant Training (PIT) for speech separation.
The code for the MaD TwinNet. Demo page:
SEGAN pytorch implementation https://arxiv.org/abs/1703.09452
Ultimate Vocal Remover Inference CLI
An official implementation of the ICASSP 2024 paper: Dual-Path TFC-TDF UNet for Music Source Separation
A PyTorch implementation of the paper: "LaSAFT: Latent Source Attentive Frequency Transformation for Conditioned Source Separation" (ICASSP 2021)
Demucs Lightning: A PyTorch lightning version of Demucs with Hydra and Tensorboard features
Banquet: A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems
An implementation of audio source separation tools.