Project description
Computer simulation for exploring musical possibilities
In his famous lectures at Harvard University in 1973, Leonard Bernstein analysed the process that led to what he called the 20th Century Crisis of Music. The EU-funded Whither Music? project, named after the motto of these lectures, will create computer models of music composition, performance, and listening that can be used to explore musical developments and alternatives, and support active exploration of the space of musical possibilities. At the heart of this will be a new approach to structured music modelling, using AI, machine learning and probabilistic modelling methods to obtain stylistically faithful, tightly controllable and transparent generative models that permit musically meaningful simulations and contribute to music information research.
Objective
"""Whither Music?"" was the motto of Leonard Bernstein's 1973 lectures at Harvard, where he analysed the (inevitable?) process that led to what he called the 20th Century Crisis of Music: the gradual decline of tonality, driven by a takeover of tonal ambiguity in the late 19th and early 20th centuries, eventually leading to complete abandonment of tonality in Schönberg's dodecaphony.
WHITHER MUSIC? is a project that aims to establish model-based computer simulation (via methods of Artificial Intelligence, Machine Learning and probabilistic modelling) as a viable methodology for asking questions about musical developments, possibilities and alternatives - for musicology, for didactic purposes, for creative music exploration scenarios. Computer simulation here means the design of predictive or generative computational models of music (of certain styles), learned from large corpora, and their purposeful and skilful application to answer, e.g. ""what if"" questions, make testable predictions, or generate musical material for further analysis, musicological or aesthetic. Making it possible to do this in highly controlled and musically 'valid' ways will require massive research on machine-learning-based music modeling, to obtain generative models that are stylistically faithful, tightly controllable, transparent and explainable - in this way advancing the field of Music Information Research (MIR). At the same time, this will open entirely new possibilities for musicological research, for music education, and for creative engagement with music, some of which will be further explored, in the form of musicological studies, didactic tools and exhibits, and public educational events.
To attain this vision, we will need to thoroughly re-think the way music is modeled in AI systems. The project wants to contribute to a redirection of MIR research towards more musically informed modeling, thus eventually addressing not only the ""Whither Music?"", but also the ""Whither MIR?"" question."
Fields of science
Programme(s)
Topic(s)
Funding Scheme
ERC-ADG - Advanced GrantHost institution
4040 Linz
Austria