GUI for a Vocal Remover that uses Deep Neural Networks.

ODAS: Open embeddeD Audition System

Ultimate Vocal Remover 5 with Gradio UI. Separate an audio file into various stems, using multiple models

Self-hostable web app for isolating the vocal, accompaniment, bass, and drums of any song. Supports Spleeter, Demucs, BS-RoFormer. Built with React and Django.

The official repo of NBC & SpatialNet for multichannel speech separation, denoising, and dereverberation

A desktop visualization GUI for the ODAS library

The BEST music separation model with help of A.I. ... to my ears ! 👂👂

Separation of upstream and downstream traffic.

Poisson pseudo-likelihood regression with multiple levels of fixed effects

Ultimate Vocal Remover CLI type for Google Colab

This GitHub repository explores the topics of privacy, anonymity and compartmentalization. These concepts are interrelated and essential for protecting one’s identity, data and online activities from unwanted surveillance, tracking and interference.

[NeurIPS 2025] Separate Anything in Audio with Zero Training

Ultimate Vocal Remover for Google Colab

Unsupervised blind source separation of mixed images and sounds with variational auto-encoders.

DeepExtractV2 – lightning-fast, high-quality audio separator. Instantly isolate vocals, drums, bass, and more from any track. Ideal for creators, DJs, and audio pros.

Pack cuda environment for bytesep music separation and provide a simple gui.

A package for decomposing multi-channel EMG signals into individual motor unit activity.

[🏆 IJCV 2025 & ACCV 2024 Best Paper Honorable Mention] Official pytorch implementation of the paper "High-Quality Visually-Guided Sound Separation from Diverse Categories"

Time-domain Audio Separation Network (IN PYTORCH)

SP-TFF code package aims to present a methodology for high-resolution polarization analysis and filtering of seismic signals in the TF-domain. The main developments in this research work are: (a) reformulation of the eigenvalue decomposition polarization analysis (EDPA) in TF-domain, (b) combining the SP-TFR to the formulation to obtain high-resolution TF-domains polarization parameters for discriminating nearby seismic phases, and (c) incorporating TF-domain directivity, rectilinearity, and amplitude attributes to extract (or eliminate) different seismic phases. The main focus is to discriminate between Love and Rayleigh from the body and coda waves.

This example decomposes a matrix into multiple matrices based on its unique values. It demonstrates array traversal, and decomposition, showing how complex structures can be broken into simpler components for analysis.

Official implementation of TISDiSS, a scalable framework for discriminative source separation.

Unofficial Pytorch implementation of SepTDA.

Translation from FOL to LTL+Past and LTL, via separation of LTL+Past

This code allows users to simulate ions confined between material surfaces that are nanometers apart, and extract the associated ionic structure.

PASF - First-Order Periodic/Aperiodic Separation Filter

PerfectPitch a music separation tool, with the backend & models of Spleeter.

This repository provides implementations for sparse graph separation, power graph experiments, and chemical property prediction.

Small library to treat request over collections as independent requests for a single resource

Kara Aerodynamics Research Laboratory