Violinmaking meets artificial intelligence

IMAGE: The historical drawing attributed to the workshop of Enrico Ceruti that inspired the outline parameterization (a) and the geometric modeling adopted in the work (b). How to predict the sound produced by a tonewood block once carved into the shape of a violin plate? What is the best shape for the best sound? These are the conclusions that researchers of the Musical Acoustics Lab of Politecnico di Milano presented in a study that was recently published in Scientific Reports. In the article "A Data-Driven Approach to Violinmaking" the Chilean physicist and luthier Sebastian Gonzalez (post-doc researcher) and the professional mandolin player Davide Salvi (PhD student) show how a simple and effective neural network is able to predict the vibrational be-havior of violin plates.