The official code repo for "Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data", in AAAI 2022

A Python toolkit for sound source separation.

A local GUI music source separation tool built on Tkinter and demucs serving as a free and open source Stem Player

Code accompanying the paper "Semi-supervised adversarial audio source separation applied to singing voice extraction"

REPeating Pattern Extraction Technique (REPET) in Matlab for audio source separation: original REPET, REPET extended, adaptive REPET, REPET-SIM, REPET-SIM online

Karaokey is a vocal remover that automatically separates the vocals and instruments. A deep learning model based on LSTMs has been trained to tackle the source separation. The model learns the particularities of music signals through its temporal structure.

REPeating Pattern Extraction Technique (REPET) in Python for audio source separation: original REPET, REPET extended, adaptive REPET, REPET-SIM, online REPET-SIM

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

Spectral Mapping of Singing Voices: U-Net-Assisted Vocal Segmentation

Piano Concerto Source Separation Pipeline

Audio Source Separation using the Non Negative Matrix Multiplication

Matlab GUI for uREPET, a simple user interface system for recovering patterns repeating in time and frequency in mixtures of sounds.

Neural network model for audio source separation task

Matlab GUIs to demo the original REPET and REPET-SIM.

Testing The Efficiency of WaveUNet as an Audio Source Separation model

This project is about summarising speech recorded in a meeting environment. It can deal with two speakers speaking at the same time, and will use audio separation derived from multiple techniques to separate and summarise the mixed audio. It provided the summary of the meeting in text form as output