AI-based.md

Voices - Guitars - Bass - Drums - Effects - MIDI - Mixing - Enhancements - Fingerprinting - Source Separation - Watermarking - Codecs - Transcription - Misc

$\color{orange}\textsf{\Largeⓘ\kern{0.1cm}\small {SORTING: Language (a>z) > License (openness) > Name / URL (a>z)}}$

Voices ⌂

Name + URL	Short description	Language	License	Last commit
Applio	Ultimate voice cloning tool, meticulously optimized for unrivaled power, modularity, and user-friendly experience
Resemble Enhance	An AI-powered tool that aims to improve the overall quality of speech by performing denoising and enhancement
Real-Time Voice Cloning	Clone a voice in 5 seconds to generate arbitrary speech in real-time

Guitars ⌂

Name + URL	Short description	Language	License	Last commit
Neural Cab	A FIR guitar cabinet simulator which generates its transfer functions by means of a Variational Auto-Encoder (VAE) trained with an additional adversarial loss and a very simple Boundary Element Method (BEM) simulation to consider the microphone position
SmartAmpPro	Guitar plugin made with JUCE that uses neural network models to emulate real world hardware
SmartGuitarAmp	Guitar plugin made with JUCE that uses neural network models to emulate real world hardware
GuitarAmp	Guitar plugin using neural networks to capture real amps and pedals
Automated-Guitar Amplifier Modelling	Neural network training scripts and trained models of guitar amplifiers and distortion pedals
GuitarLSTM	Deep learning models for guitar amp/pedal emulation using LSTM with Keras
NAM: neural amp modeler	Neural network emulator for guitar amplifiers
CNN Distortion	Combine deep learning and DSP
Deep Guitar Amplifier	A little project to practice Tensorflow/Keras where I use deep learning for black-box modelling of a guitar amplifier

Bass ⌂

Name + URL	Short description	Language	License	Last commit
Walking Bass Transcription	Algorithm for walking bass transcription in jazz ensemble recordings using Deep Neural Networks (DNN)
BassUNet	Algorithm for bass transcription (joint frame-level pitch and voicing estimation) using U-Net Fully Convolutional Networks
bassTranscriber	Automatically transcribing bass lines using neural networks
Beatle-Basslines	Deep Learning model for creation of an instrument track in a performer's style from Other tracks in a MIDI file

Drums ⌂

Name + URL	Short description	Language	License	Last commit
Automatic Drum Transcription	Automatic drum transcription using neural nets
Mix-Wave-U-Net	Implementation of the Mix-Wave-U-Net for automatic mixing of drums
NeuralDrummer	A neural network for generating drum tracks for songs
Neural-Networks-for-Drum-Music-Generation	Generating realistic drum music using LSTM neural networks trained on rock-style MIDI drum performances
Automatic drums transcription using neural networks	Internship's code for automatic drums transcription with neural networks
drumsep	A Convolutional Neural Network for drum signal separation from full mixes
Generative Adversarial Networks - Drum Pattern Generation	It generates drum patterns similar to those by Maciej Kowalski

Effects ⌂

Name + URL	Short description	Language	License	Last commit
OpenVINO™ AI Plugins for Audacity	A set of AI-enabled effects, generators, and analyzers for Audacity®
GRAND MATRON	An audio neural network plugin modeling a low pass filter
AI Compressor	Implementing an Intelligent Dynamic Range Compressor Using Machine Learning Approaches

MIDI ⌂

Name + URL	Short description	Language	License	Last commit
NeuralNote	Audio Plugin for Audio to MIDI transcription using deep learning
Notochord	A real-time neural network model for MIDI performances
RoboDrummer	Midi drums generator based on deep neural network

Mixing ⌂

Name + URL	Short description	Language	License	Last commit
Evolving artificial neural networks for cross-adaptive audio effects	Analysis of various features of the audio signal is used to adaptively control parameters of audio processing of the same signal
automix-toolkit	Models and datasets for training deep learning automatic mixing models
DJtransGAN	Automatic DJ Transitions with Differentiable Audio Effects and Generative Adversarial Networks
MixCNN	Mulitrack mix leveling with convolutional neural nets
AudMIX	A web-based system for processing Audio using Deep Learning
deep-audio-mixer	Deep Learning based system for audio mixing

Source Separation ⌂

Name + URL	Short description	Language	License	Last commit
audioss	Audio source separation tool using a neural network
DeepConvSep	Deep Convolutional Neural Networks for Musical Source Separation
Audio Source Separation using Low Latency Neural Network	PyTorch code based on "Monoaural Audio Source Separation Using Deep Convolutional Neural Networks" to separate instruments from music using a low-latency neural network
A Wavenet for Music Source Separation	A neural network for end-to-end music source separation
BS-RoFormer	Implementation of Band Split Roformer, SOTA Attention network for music source separation
GAN_SASS_TF	TensorFlow implementation of "GAN Single Audio Source Separation"
Open-Unmix for PyTorch	PyTorch (1.8+) implementation of Open-Unmix, a deep neural network reference implementation for music source separation
Ultimate Vocal Remover GUI	GUI for a Vocal Remover that uses Deep Neural Networks
Audio Source Separation	Deep Neural Network model for Audio source separation
BandIt: Cinematic Audio Source Separation	Code for "A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation" paper
CASS	CROSS ADVERSARIAL SOURCE SEPARATION VIA AUTOENCODER
GENERATIVE ADVERSARIAL SOURCE SEPARATION	Generative sourceseparation with GANs
Unmixer	A GUI frontend for LALAL.AI's AI-powered stem-splitting technology
deeper-wider-melody	Accompanying code for the "Enhancing Vocal Melody Extraction with Multilevel Contexts" paper

Enhancements ⌂

Name / URL	Short description	Language	License	Last commit
Audio-Undistortion	Audio Signal Processing for Undistorting Audio Clips
Audio-Enhancement-GAN	This is a Audio enhancement system which uses GAN
audio-sr-deep-unfold	A deep learning-powered toolkit for super-resolution in sparse microphone arrays
AudioSR	Versatile Audio Super-resolution at Scale
AURAL_GAN+predictive_model	Aims to transform low-quality phone recordings into professional-quality audio using a Generative Adversarial Network (GAN)
Stochastic-Restoration-GAN	Stochastic Restoration of Heavily Compressed Musical Audio using Generative Adversarial Networks in Pytorch
Audio Cycle GAN	GAN improving poorly synthesized audio samples
Audio Enhancement with Deep Learning	Denoising and upsampling audio files using DNN architectures such as autoencoders, SEGAN and WaveNet
Audio Super Resolution	Enhancment of Audio Quality (Bit-Depth and Sampling-Rate) using Deep Learning
GAN_decoded_audio_enhancement	Unofficial PyTorch Implementation of "Audio codec enhancement with generative adversarial networks" paper
Grosbeak	Audio quality manipulation experiment using deep learning
NMGAN	A GAN designed to upsample low-quality audio

Fingerprinting ⌂

Name + URL	Short description	Language	License	Last commit
neural-audio-fp	Neural Audio Fingerprint for High-specific Audio Retrieval based on Contrasive Learning
FingerprintDNN	Fast pitch detection using a deep neural network trained on audio fingerprints
pfann	Neural Audio Fingerprint for High-specific Audio Retrieval based on Contrasive Learning

Watermarking ⌂

Name + URL	Short description	Language	License	Last commit
DNN-audio-watermarking	A robust DNN-based audio watermarking system
WavMark	AI-based Audio Watermarking Tool
IDEAW	Robust Neural Audio Watermarking with Invertible Dual-Embedding

Codecs ⌂

Name + URL	Short description	Language	License	Last commit
AudioCodec-Hub	A Python library for encoding and decoding audio data, supporting various neural audio codec models
Descript Audio Codec	A high fidelity general neural audio codec
EnCodec	State-of-the-art deep learning based audio codec
encodec-pytorch	unofficial implementation of the High Fidelity Neural Audio Compression
NeuralAudio	Sound compression based on Growing Self-Organizing Maps
Siamese SIREN	Audio Compression with Implicit Neural Representations
SoundStream	An end-to-end neural audio codec
audiolite	A deep learning framework for audio compression and decompression

Transcription ⌂

Name + URL	Short description	Language	License	Last commit
audioFlux	A deep learning tool library for audio and music analysis, feature extraction
Automatic Transcription via DL	Deep learning Japanese instruments - flute and drum - automatic transcription

Misc ⌂

Name + URL	Short description	Language	License	Last commit
whisper.cpp	High-performance inference of OpenAI's Whisper automatic speech recognition (ASR) model
DRC	Digital Room Correction (DRC) made with a deep neural network
Bleeding Removal in Music Signals	Neural networks for removal of bleeding in music signals for the sequential application of Music Source Separation
Musical-Accompaniment-GAN	Deep Learning project to create a model for accompaniment of piano tracks with guitar, strings, bass and drums
Audio-Denoiser	Audio Denoiser implemented by CNN and GAN