Midi event transformer for symbolic music generation

PDMX: A Large-Scale Public Domain MusicXML Dataset for Symbolic Music Processing

Code and demo for paper: Zhao et al., Structured Multi-Track Accompaniment Arrangement via Style Prior Modelling, in NeurIPS 2024.

This is the official implementation of MusER (AAAI'24).

A library for computing Frechet Music Distance.

A transformer neural network that generates symbolic music improvising over chord changes.

This is the official implementation of RL-Chord (TNNLS).

A transformer model for generating solo piano compositions. Generetes quantized output suitable for working in DAWs.

The Pop-K MIDI Dataset contains 305,815 training examples of augmented pop melodies.

all-in-one ai-midi-pipeline

This repository contains the code for the paper On the Joint Minimization of Regularization Loss Functions in Deep Variational Bayesian Methods for Attribute-Controlled Symbolic Music Generation, submitted to EUSIPCO 2025.

Demo for PDMX: A Large-Scale Public Domain MusicXML Dataset for Symbolic Music Processing