music-source-separation-using-Unets
asteroid
music-source-separation-using-Unets | asteroid | |
---|---|---|
1 | 2 | |
20 | 2,111 | |
- | 1.7% | |
1.8 | 5.5 | |
10 months ago | 25 days ago | |
Python | Python | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
music-source-separation-using-Unets
-
Music source separation system using deep learning. Developed in Python
Please have a look at the project repo and read my project report where I explained the system in detail.
asteroid
- Speech separation
-
[D] Is it possible to extract certain sounds from a mixture of sounds and noise
Here is a link to a tutorial about that will teach you everything you need to know about source separation, from data, to losses, to commonly used model architectures. That tutorial is built around the nussl source separation library, but some other nice ones exist as well, such as asteroid.
What are some alternatives?
stemroller - Isolate vocals, drums, bass, and other instrumental stems from any song
nussl - A flexible source separation library in Python
demucs - Code for the paper Hybrid Spectrogram and Waveform Source Separation, but the goddamm motherfucker doesn't work.
Conv-TasNet - A PyTorch implementation of Conv-TasNet described in "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation" with Permutation Invariant Training (PIT).
spleeter - Deezer source separation library including pretrained models.
Wave-U-Net-for-Speech-Enhancement - Implement Wave-U-Net by PyTorch, and migrate it to the speech enhancement.
Speech-Separation-Paper-Tutorial - A must-read paper for speech separation based on neural networks
mmf - A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
voicefilter - Unofficial PyTorch implementation of Google AI's VoiceFilter system
mayavoz - Pytorch based speech enhancement toolkit.
huggingface_hub - The official Python client for the Huggingface Hub.