an extremely simple tool for separating vocals and background music, completely localized for web operation, using 2stems/4stems/5stems models 这是一个极简的人声和背景音乐分离工具，本地化网页操作，无需连接外网

A must-read paper for speech separation based on neural networks

Record, concatenate and synchronize Twitch live streams and remove background music

Implementing the paper -

Reproduction of the paper SFSRNet: Super-resolution for single-channel Audio Source Separation by me (@arda-num) and @dritx16. Navigate Project_Ates_Numanoglu folder to see.

Large publicly available speech datasets

Code for the paper Musical Voice Separation as Link Prediction: Modeling a Musical Perception Task as a Multi-Trajectory Tracking Problem

Video Subtitles Extraction,Audio and Video Content Recognition and Analysis

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

Solves the "Cocktail Party Problem" using ReSpeaker 4-Mic Array & AuxIVA (BSS). Features a real-time AI Tutor pipeline (Whisper + GPT-4o) for simultaneous multi-speaker interaction.

A QT frontend app for Demucs- and Spleeter-based audio stem separation.

Thesis project for Speech Separation using Deep Learning

DESIGN AND IMPLEMENTATION OF AN EMBEDDED SYSTEM FOR AYTOMATIC SEPARATION OF CONCURRENT SPEAKERS