Musik & Mathematik

  • Katarzyna Grebosz-Haring (Chair)
  • Bathke, A. (Chair)
  • Martin Losert (Organisator/in)
  • Mark Gotham (Session chair)

Aktivität: Mitwirkung an und Organisation einer VeranstaltungOrganisation einer Veranstaltung

Beschreibung

Online-Vortrag

Beethoven X: Es könnte sein (It could be … )

Mark Gotham
Institut of Musicology, Saarland University, Saarbrücken, DE

2020 saw the 250th anniversary of Beethoven’s birth. Among the many celebrations taking place, one that captured the imagination of the international public and press was a project initiated and funded by Deutsche Telekom to create a realization of Beethoven’s fragmentary sketches for a 10th symphony using machine learning. This project brought together a team of music and computer science experts (including the present author) to make all the necessary musicological and computational decisions about how to take on this intriguing task. This talk will go through some key decisions in each constituent part of that process, including: making sense of Beethoven’s scant and fragmentary plans for this work, converting those ideas into a machine-readable format, identifying suitable music generation tasks (extending a sketched melody, adding an accompaniment … ), identifying and sourcing suitable training materials for each task (depending on the mature of the musical materials), and the curatorial decision-making process over which generations to use. We cast this as a possible prototype for future human-machine interactions – harnessing the processing powers now available to us, while giving human author(s) the final say. Additionally, we also portray this as not so dissimilar from traditional (non-computational) methods of composing which similarly involve the processing of options (informed by a large corpus of prior musical work) and the judicious selection thereof.
Zeitraum29 Apr. 2021
VeranstaltungstypOnline-Vortragsreihe
BekanntheitsgradInternational

Schlagwörter

  • Computermusik
  • Future human-machine interaction
  • Musikwissenschaft