Exploring the future of Classical Music

As described by Lionel Esparza, French musicologist, musician and radio producer (France Musique) in 2021, classical music is in decline. The reasons are various such as ageing of the audience, cultural shift and mismatch. At the same period, two major observations arose from the discussions between the Verbier classical music festival and the EPFL+ECAL Lab: first, the number of people listening to classical music and participating in the festival is decreasing. Secondly, the full experience of classical music shows, e.g feeling of vibrations or perception of interpretation, is accessible to only a few privileged people such as experts, musicians, conductors and VIPs in the front row. These factors, among many others, can be perceived as discouraging for young or non-expert audiences when they come to the festival. 

To face this decline and bring back young and non-expert audiences back to the festival, EPFL+ECAL Lab proposes to endow the Verbier Festival with an innovative space dedicated to explore the future of classical music. Within this space, through interaction between masters and young musicians, musicians and spectators will have the opportunity to listen, feel and explore the music differently. Thanks to a multimodal playful interpretation of the music, we hope to foster engagement among a larger audience. 

To face this challenge, we hypothesise that classical music features should be augmented. A way to do it is to use those features to feed kinetic sculptures.

The first step to reach the objectives and the main topic of the proposed project here, is to extract, in an automatic manner, the features of such audio content. Several ways and possibilities exist such as variational autoencoder, wavelet analysis, spectral analysis, cross correlation to name a few. In this project, we wish to investigate which techniques are best to extract features to be playback into an interactive installation. The ultimate goal of the overall project is to create an interactive space dedicated to classical music.

The involved student will be part of the EPFL+ECAL Lab team conducting the design research project composed of engineers, designers, and psychologists. The final overall project will be displayed during the Verbier festival in July 2023.

Key Domains

  • Machine learning
  • Signal processing


  • Some knowledge of machine learning, deep-learning.
  • Basics in signal processing
  • Proficiency in Python.