Machine Learning’s Potentials in Composition, Performance and Reception of Contemporary Music: Multimodal Analysis of Recent Mixed Music Works
As a highly structural form of art, music has led to numerous attempts to use automatic generation methods for its composition, at first mostly derived from symbolic artificial intelligence techniques such as generative grammars, evolutionary algorithms or cellular automata. Those methods can be used by composers for the idiosyncratic extension of their creative processes, the creation of compositional tools, the implementation of musical theories and/or specific styles, or the programmatic modeling of cognitive theories.
Recently, new composer-centered research-creation projects based specifically on machine learning systems have been launched (Bresson & al. 2018; Sturm & Ben-Tal 2021; Anders 2022…). These systems have rarely been used by composers as a tool designed to assist the composer. They differ from symbolic artificial intelligence systems which are based on a complex system of rules for inference and production of structure and/or musical material. Non-linear and dynamic, machine learning systems consist of a multitude of interconnected procedural units that interact with each other. Inspired by the functioning of the human brain, they are capable of learning, being trained, generalizing and abstracting contradictory data. Thus, the importance of the “memory” of such systems and its impact on compositional processes raises a lot of new questions.
American composer Ted Moore writes numerous multimodal mixed music works using machine learning methods, tailored to his creative process and artistic concepts. In alloy, composed in 2018 for feedback cymbal, multiphonics and electronics, machine learning techniques support both the pursuit, the listening of the performers and their response in relation to the present musical moment. In feed, composed the same year for bassoon and live electronics, machine-learning techniques open artistic multimodality by linking timbre and light shifts. Paradoxically, in these works, the degree of openness enabled by machine learning is matched only by the strong control over parameters intrinsic to timbres and their use in both compositional and performance processes. The works’ degree of openness also raises the question of the archiving and preservation of contemporary music employing automatic generation methods. The notion of memory, which we will discuss in this presentation, seems to play a role in both the algorithms and the man-machine interactivity of mixed music composed using such techniques.
According to Roger Dannenberg, the literature dedicated to the study of the use of artificial intelligence and machine learning methods in musical composition focuses on the description and programming of tools and software intended for creation, but rarely on the composer’s intentions. With access to Moore’s archives and thanks to our interviews with the composer, we aim to analyze the artistic choices and implementation strategies of machine learning techniques in his creative process. Our study will aim to shed light on the motivations underlying the use of these tools, as well as the ways in which they influence and shape the aesthetics and structure of the work, thus contributing to a better understanding of the dynamics between composers and technology in contemporary musical composition
Keywords: new technologies, creative process, sketch studies
Biography
Florian Iochem is PhD candidate in musicology at the University of Strasbourg and Aix-Marseille University. His research interests range from 20th- and 21st-century music historiography to computer-assisted musical analysis, analysis of composer archives, psychology of music perception and musical aesthetics. As part of his PhD dissertation (co-directed by Anne-Sylvie Barthel-Calvet and Vincent Tiffon), he is particularly interested in the impact of the emergence of artificial intelligence in mixed music and the potential paradigmatic break that this implies. As student member of the international ACTOR project (Analysis, Creation and Teaching of Orchestration), he took part as a research assistant in the APCOR (Analysis of Creative Practices in Orchestration, dir. Nathalie Hérold and Gilbert Nouno) and is a member of the East Asian Music research group (dir. Robert Hasegawa). Since 2022, he has been responsible for the administrative management of the French Society for Music Analysis.
University of Strasbourg, France
florian.iochem@etu.unistra.fr