See all projects

To what extent can machine learning find a suitable musical accompaniment for a given melody?

Pierre
Pierre
High School
Ecole Moser Geneve
Graduation Year
2023
Student review
Everything was good.

View Polygence scholar page
Project description

Music generation using machine learning and AI has been a topic of interest over the past few years. Music proves to be a complex task for AI, as it is an art of time, is heavily influenced by human intuition, and is often composed polyphonically where all instruments are interdependent. However, audio data has several interesting features for a machine learning model. In fact, it follows a strict tempo, is pitch-related, and when defining a strict genre or style, some patterns can be found in the way music is created. Currently, most multi-track music generation models use CNN (Convolutional Neural Network), and music is often generated using only very general training data, not allowing a user to generate music according to a specific melody.

In this paper, we present a VAE-based (Variational Autoencoder) machine learning model that is able to generate a musical accompaniment to a user-given melody. The master melody is inputted by the user and a VAE works with a Convolutional Neural Network to find a musical accompaniment to the inputted melody. Unlike current existing models, which generally generate music from scratch after listening to many samples, this one allows any user to enrich their wanted melody. We trained our model on different genres to produce different styles of accompaniment to the melody. Not only does it perform better than state of the art CNNs, but it also gives the user more influence on the outputted music, allowing him to give the first main melodic idea.

To what extent can machine learning find a suitable musical accompaniment for a given melody?
Project outcome

Our generation can be found at https://on.soundcloud.com/aJwDY


Shomik
Shomik
PhD Doctor of Philosophy candidate
Subjects
Arts, Engineering, Chemistry, Comp Sci
Expertise
Renewable energy (solar), heat transfer, computational materials science
Mentor review

I could really feel his experience and his ability to understand my issues/solve them.

Interested in starting
your own project?
Apply today!

OR
Already have an account? Log In
By registering you agree to our terms of use and privacy policy, and consent that we or our partner provider may reach out to you using a system that can auto-dial.