You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The core of my graduation project that uses convolutional neural networks to extract the vocal part from a song by removing the sound of musical instruments. The project is rather academic, it did not achieve too great real results, but this is expected. I'm not going to develop it further.
Self-hostable web app for isolating the vocal, accompaniment, bass, and drums of any song. Supports Spleeter, D3Net, Demucs, Tasnet, X-UMX. Built with React and Django.
This repository focuses on algorithms, models, and techniques for isolating and extracting individual sources from mixed audio signals using advanced machine learning methods.
A single-channel source separation project that aims to determine the speakers at a given time and estimate each speaker's total speaking time from the audio recordings.
A course project for DA 623: Computing with Signals. We investigate the use of Non-negative Matrix Factorization for speaker diarization and source separation.