UNet-VocalSeparation-Chainer
by Xiao-Ming
A Chainer implementation of U-Net singing voice separation model
AI summary
Voice separator
An implementation of U-Net singing voice separation model using Chainer framework
- stars
- 90
- forks
- 23
- watching
- 8
Similar projects
Found by comparing what the projects do, not just their names.
Singing voice separator
This project provides a PyTorch implementation of a singing voice separation algorithm using recurrent inference and skip-filtering connections.
Audio separator
A collection of MATLAB-based deep learning models and tools for source separation tasks in audio processing
Speech separator
An implementation of a speech separation algorithm using neural networks.
Audio separator
A C++ project that creates a VST interface to the Spleeter audio separation tool.
Music source separation
A deep neural network model for separating singing voice from music in audio files
Syllable segmentation tool
An implementation of a score-informed method for segmenting jingju a cappella singing voice into syllables using convolutional neural networks and Viterbi algorithm
Sound separator
An audio separation model that can process open-domain sound descriptions to separate different sounds from mixed audio.
Voice separation library
An implementation of Google AI's VoiceFilter system using PyTorch.
yxlllc/ddsp-svc1.9K
Voice converter
Real-time end-to-end singing voice conversion system using DDSP models and various machine learning techniques
Syllable breaker
Provides algorithms for breaking down words into their constituent syllables.
Speech separator
A Matlab toolbox for supervised speech separation using deep neural networks
Voice Model
An end-to-end voice model for conversational dialogue in English
Deblurring model
Develops a deep learning model for single image deblurring with improved performance and computational efficiency
EcomModel
An Instruction-Following Large Language Model designed to perform tasks in the e-commerce domain
Seq2seq library
A Python NLP library for training and running sequence-to-sequence models similar to the fast.ai library.
