mamezy

LivePortrait

Bring portraits to life!

ComfyUI

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

musiclang

ChromaTone

Color to Sound

midi-rnn

Generate monophonic melodies with machine learning using a basic LSTM RNN

muzic

Muzic: Music Understanding and Generation with Artificial Intelligence

audio_embeddings

Audio search using Azure Cognitive Search

MusiCNN-embeddings

The project consists in evaluating music similarity and building a genre classifier using song embeddings from GTZAN dataset extracted with Essentia’s MSD-MusiCNN model.

models

Models and examples built with TensorFlow

Audio-Denoiser-CNN

conditional-similarity-networks

cosernn

Code for the paper "Contextual and Sequential User Embeddings for Large-Scale Music Recommendation".

spotifytrack

A personal homepage showing users' top songs and artists, providing a shareable link that they can use to show it off to friends.

vocalsound

Dataset and baseline code for the VocalSound dataset (ICASSP2022).

fingerprintjs

Browser fingerprinting library. Accuracy of this version is 40-60%, accuracy of the commercial Fingerprint Identification is 99.5%. V4 of this library is BSL licensed.

coversong_identification

Cover song identification using 2DFT sequences

deep_hashing_coverSongDetection

Cover Song Detection System

CoverHunter

Official PyTorch implementation of CoverHunter

FastCqt

Fast constant-Q transform feature, c++ implement

setlist_id

DeepBach

code accompanying "DeepBach: a Steerable Model for Bach Chorales Generation" paper

mustango

Mustango: Toward Controllable Text-to-Music Generation

song-recognition

Full-stack song recognition application with audio fingerprinting and hum to search (QbSH) modules

cross_version_learning

Code for the paper "A Cross-Version Approach to Audio Representation Learning for Orchestral Music", ISMIR 2023

CHAD

Official Code of "A Semi-Supervised Deep Learning Approach to Dataset Collection for Query-by-Humming Task" (ISMIR 2023)

qbh-cuda

This project is a algorithm the Query-By-Humming (QBH) based on melody warping (Dinamic Time Warping) and inspired on https://www.hindawi.com/journals/tswj/2014/614193/

Hum-to-song

An API that takes vocal input, identifies most probable song match and returns the list of matching songs. Helps users identify that unknown song title with just a hum or sung melody.

inaSpeechSegmenter

CNN-based audio segmentation toolkit. Allows to detect speech, music, noise and speaker gender. Has been designed for large scale gender equality studies based on speech time per gender.

NeuralNote

Audio Plugin for Audio to MIDI transcription using deep learning.

METU-TRADEMARK-DATASET