DeepConvSep
Music source separation
A framework for training deep neural networks to separate music sources from audio files.
Deep Convolutional Neural Networks for Musical Source Separation
472 stars
34 watching
110 forks
Language: Python
last commit: almost 5 years ago audio-synthesisconvolutional-neural-networksdata-augmentationdata-generationdeep-learningsample-queryingscore-synthesissignal-processingsource-separationtheano
Related projects:
| Repository | Description | Stars |
|---|---|---|
 andabi/music-source-separation | A deep learning model for separating singing voice from background music in audio files | 798 |
 posenhuang/deeplearningsourceseparation | A collection of MATLAB-based deep learning models and tools for source separation tasks in audio processing | 366 |
 l0sg/seqgan-music | Generates polyphonic music sequences using deep learning models and adversarial training | 28 |
 kristijanbartol/deep-music-tagger | Classifies music genres using a deep neural network model trained on a large audio dataset | 67 |
 salu133445/musegan | Generates polyphonic music from scratch or based on user input using a neural network architecture | 1,846 |
 calclavia/deepj | A deep learning model that generates music with tunable properties based on specific styles | 728 |
 deepsound-project/samplernn-pytorch | An implementation of an audio generation model using PyTorch | 288 |
 despoisj/deepaudioclassification | Automatically categorizes music genres using deep learning algorithms | 1,097 |
 js-mim/mss_pytorch | This project provides a PyTorch implementation of a singing voice separation algorithm using recurrent inference and skip-filtering connections. | 171 |
 chrisdonahue/wavegan | An open-source machine learning algorithm for generating raw audio waveforms from raw data | 1,330 |
 soroushmehr/samplernn_iclr2017 | An unconditional end-to-end neural audio generation model utilizing a recurrent neural network architecture. | 537 |
 brunnergino/jambot | A music generation tool that uses chord embeddings and neural networks to create polyphonic music with harmonic structure | 64 |
 mlachmish/musicgenreclassification | Classify music genre from a 10-second sound stream using a neural network. | 562 |
| mtg/dunya-desktop | A desktop application for visualizing and accessing music data through a modular interface. | 89 |
 keunwoochoi/icassp_2017 | A repository containing code and pre-trained models for music classification using Convolutional Recurrent Neural Networks. | 12 |