# Demonstration of PerformanceNet: A Convolutional Neural Network Model for Score-to-Audio Music Generation

## TL;DR

PerformanceNet is a neural network that converts musical scores into audio, automatically adding performance nuances and synthesizing realistic music, representing an AI performer that interprets scores creatively.

## Contribution

This paper introduces PerformanceNet, a novel neural network model that performs score-to-audio conversion with automatic performance attribute learning, advancing AI-driven music synthesis.

## Key findings

- Successfully converts scores to audio with performance nuances
- Automatically learns performance attributes like velocity changes
- Produces realistic and expressive synthesized music

## Abstract

We present in this paper PerformacnceNet, a neural network model we proposed recently to achieve score-to-audio music generation. The model learns to convert a music piece from the symbolic domain to the audio domain, assigning performance-level attributes such as changes in velocity automatically to the music and then synthesizing the audio. The model is therefore not just a neural audio synthesizer, but an AI performer that learns to interpret a musical score in its own way. The code and sample outputs of the model can be found online at https://github.com/bwang514/PerformanceNet.