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

Singing Voice Separation via Recurrent Inference and Skip-Filtering Connections - PyTorch Implementation. Demo:

C++17 port of Demucs v3 (hybrid) and v4 (hybrid transformer) models with ggml and Eigen3

The code for the MaD TwinNet. Demo page:

An official implementation of the ICASSP 2024 paper: Dual-Path TFC-TDF UNet for Music Source Separation

Sound Demixing Challenge 2023

Banquet: A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems

Pytorch implementation of subband decomposition

Gradio WebUI for whisper, faster-whisper, whisper-timestamped. Supports YouTube Downloader, Vocal Remover and Transcription.

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

Source Separation training codebase for the Sound Demixing Challenge 2023.

logWMSE, an audio quality metric & loss function with support for digital silence target. Useful for training and evaluating audio source separation systems.

Variations of L1 SNR Loss function for training audio source separation machine learning models

Create and explore isolated tracks from music files

Official repo of ICASSP 2022 paper - Don't Separate, Learn to Remix: End-to-End Neural Remixing with Joint Optimization

Support material and source code for the system described in : "New Sonorities for Jazz Recordings: Separation and Mixing using Deep Neural Networks".

Support material and source code for the model described in : "A Recurrent Encoder-Decoder Approach With Skip-Filtering Connections For Monaural Singing Voice Separation"

Carnatic singing voice separation trained with in-domain data with leakage

Pytorch implementation of MDensenet and sparse NMF. Made for my undergraduate thesis "Music Source Separation with Supervised Learning Methods".

MUSION, a toolbox for music information retrieval and music signal processing.

eCMU: An Efficient Phase-aware Framework for Music Source Separation with Conformer (IEEE RIVF23)

GGML-based C++ inference for BS Roformer/Mel-Band-Roformer vocal separation | 纯 C++ 实现的基于 GGML 的 BS Roformer/Mel-Band-Roformer 人声分离推理

This is a project for Columbia Research Project

This project create an api to upload files and download after Spleeter processing.

Tensorflow 2.x (with Keras API) Implementation of the TaSNet (Luo et al., 2018)

No description provided.

[WIP] PyTorch implementation of the DTTNet deep learning architecture, trained on MUSDB18-HQ 🎸

No description provided.

Neural Networks for Interference Reduction in Multi-track Recordings. The Convolutional Autoencoders (CAEs) and the truncated-UNet (t-UNet).

No description provided.