sound-separation
Here are 11 public repositories matching this topic...
Language:All
Sort:Most stars
Codebase for ECCV18 "The Sound of Pixels"
- Updated
Apr 25, 2022 - Python
The code for multi-channel source separation and dereverberation such as FastMNMF1, FastMNMF2, and AR-FastMNMF2.
- Updated
Oct 16, 2022 - Python
Co-Separating Sounds of Visual Objects (ICCV 2019)
- Updated
Jul 25, 2023 - Python
logWMSE, an audio quality metric & loss function with support for digital silence target. Useful for training and evaluating audio source separation systems.
- Updated
Jan 29, 2026 - Python
Variations of L1 SNR Loss function for training audio source separation machine learning models
- Updated
Feb 4, 2026 - Python
🎤 Vocal Remover for Karaoke (on-going..)
- Updated
Aug 14, 2018 - JavaScript
PyTorch implementation of "Leveraging Category Information for Single-Frame Visual Sound Source Separation"
- Updated
Aug 1, 2021 - Python
Sound Filter is a software that uses frequency analysis and filter design to separate mixed sounds into two tracks. It utilizes the Bilinear transform and low-pass/high-pass filters to isolate original sounds from mixed recordings. Ideal for audio engineers and technicians.
- Updated
Mar 16, 2023 - MATLAB
Clojure bindings for PyTorch implementation of Open-Unmix
- Updated
Mar 21, 2024 - Clojure
PATCHBAY is a desktop GUI and a small Python backend for running the facebook/SAM-Audio family of models
- Updated
Feb 1, 2026 - Python
This repository stores work on a sound separation project of Bird sounds. The goal is to separate a mixture of frequencies into bird calls and noise. It is inspired by MixIT and Asteroid.
- Updated
Dec 1, 2024 - Jupyter Notebook
Improve this page
Add a description, image, and links to thesound-separation topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with thesound-separation topic, visit your repo's landing page and select "manage topics."