Gaëtan Hadjeres

Putting composers back in the loop

Applying the latest deep learning techniques to music composition is appealing for AI researchers; but for composers, this intrusion of machines in their domain of expertise could be perceived as a threat. This fear of being replaced is legitimate: indeed, many recent generative models for music tend to produce infinite numbers of
scores without the need for human intervention. I think that this behavior is not desirable and that AI algorithms should instead be used by artists as assistants during the compositional process. By creating a fruitful discussion between a composer and the machine, the artist can then focus on the development of their musical ideas and let the AI do the technical parts. Professional composers can benefit from these tools to become more productive and explore uncharted regions of musical creation while amateur musicians can use these innovative tools to express themselves in an intuitive way. By putting composers back in the loop, we will go from automatic music composition to AI-augmented composition and redefine the way people compose music.

Artificial Intelligence / Interactive Deep Generative Models /
AI-augmented Music Composition / Bach Chorales / Information Geometry

Selected Publications

DeepBach: a Steerable Model for Bach Chorales Generation;
Gaëtan Hadjeres, François Pachet, Frank Nielsen;
Proceedings of the 34th International Conference on Machine Learning,
ICML 2017, Sydney, NSW, Australia, 6-11 August 2017.

Interactive Music Generation with Positional Constraints using
Gaëtan Hadjeres, Frank Nielsen;
arXiv:1709.06404, 2017

GLSR-VAE: Geodesic Latent Space Regularization for Variational
AutoEncoder Architectures;
Hadjeres, Gaëtan, Frank Nielsen, François Pachet;
IEEE Symposium Series on Computational Intelligence (IEEE SSCI

Monte Carlo Information Geometry: The dually flat case;
Frank Nielsen, Gaëtan Hadjeres;
arXiv:1803.07225, 2018


Gaëtan Hadjeres graduated from the École Polytechnique (France) and
obtained a master in Pure Mathematics from Paris 6 University
(Sorbonne Universités). He joined Sony CSL Paris in 2014 to do
a Ph.D. thesis on music generation under the supervision of
François Pachet and Frank Nielsen. In 2018, Gaëtan successfully
defended his dissertation entitled "Interactive Deep Generative Models for
Symbolic Music" and is now a permanent member of the Sony CSL Paris
Music Team. Parallel to his scientific background, he studies music
composition at the Conservatoire de Paris (CNSMDP). He is also a
pianist and a double bass player.


Go to top