Emmanuel Deruty


エマニュエル・デルティ Emmanuel Deruty
Any music you can(not) imagine

Globalization has led popular music to become a part of a universal world culture. The conventions of music have departed from local preferences to a universally shared language.

Additionally, cheap personal computers have brought million-dollar studios to people’s homes. Everybody’s a music producer. A plethora of virtual instruments, audio processes, and sample libraries are readily available.

A universal language, loads of data: it’s time to look for an understanding of the universal principles of music. Can we define universal principles of well-formedness in music?

The path to such knowledge goes through the augmentation of human capacities of observation using cutting-edge machine learning algorithms.

When algorithms of automatic music generation grow to possess this knowledge, then we can generate music from any material, music from the strangest idea, any music you can(not) imagine.



Artificial intelligence / Neural networks / Deep learning / Music composition / Music production / Automatic mixing

Selected Publications

Emmanuel Deruty and François Pachet. "Why is studio production interesting?» Tutorial T3 at ISMIR 2016. Columbia University, NYC, USA, Aug. 6th, 2016. <Link to the tutorial>

Emmanuel Deruty and Damien Tardieu. "About Dynamic Processing in Mainstream Music." Journal of the Audio Engineering Society, vol. 62, issue 1/2, pp. 42-55 (Jan. 2014).

Frédéric Bimbot, Emmanuel Deruty, Gabriel Sargent and Emmanuel Vincent . "System & Contrast: A Polymorphous Model of the Inner Organization of Structural Segments within Music Pieces." Music Perception, vol. 33 no. 5 (Jun. 2016)

Short bio

Emmanuel Deruty graduated from the Conservatoire de Paris (CNSMDP), Paris, France. Before Sony CSL, he has worked as a sound designer for IRCAM, Paris, France and Soundwalk, New York, NY, as a film music composer in Europe and in the US, as a writer for the Sound on Sound magazine, Cambridge, UK, as a consultant in musicology applied to M.I.R. for INRIA, Rennes, France, and as part of the research teams for IRCAM and Akoustic Arts, Paris, France.