Artificial Models for Music Creativity: Part 2

Fach

CoPeCo, E-1-Jko-MM, Tec-W1-MMK, Tec-W2-MMK, W-bv, W-frei, Wiss-1-MMK

Lehrende

Alessandro Anatrini

Termin

ELA 5 each meeting from 10 to 17: 13.4, 4.5, 25.5, 2.6, 8.6

Raum

ELA 5 (Grün 005)

Dauer

1.5 Semesterwochenstunden

Beschreibung

This course offers a comprehensive blend of hands-on experience and theoretical foundations for integrating machine learning models into artistic practices, with a particular focus on music applications. Spanning across two semesters, each segment comprises assignments and a laboratory component. "Artificial Models for Music Creativity" convenes as a block seminar once a month during each semester.

Throughout the course, we will explore the dynamic intersection of machine learning and artistic expression, specifically within the realm of music. Our primary emphasis will center on prominent models for audio generation, including Variational Autoencoders (VAE) and Generative Adversarial Networks (GAN).

In Semester 2, the focus shifts towards audio generation across diverse platforms and the automatic preprocessing and training of audio datasets. Within this module, we will delve into the utilization and training of RAVE - https://github.com/acids-ircam/RAVE - across various contexts such as IDEs, Jupyter notebooks, Max, and Standalone VST. Significantly, the course will highlight the collaborative process of curating a cohesive audio dataset, implementing proper preprocessing techniques, leveraging its contents for training routines, and utilizing the resulting model weights to generate audio for artistic endeavors.

Literatur

The reference literature will be provided by the instructor during the first lesson.

Credits

4 Creditpoints

Bemerkung

The course does not require prior knowledge of Python; however, interested students are encouraged to contact the instructor before the start of the class at alessandro.anatrini[at]hfmt-hamburg.de
The course is offered in person in the English language.

Module

CoPeCo, Multimediale Komposition (Jazzkomposition Master), Technisches Wahlmodul 1 Multimediale Komposition Master, Technisches Wahlmodul 2 Multimediale Komposition Master, Berufsvorbereitendes Wahlmodul Master, Wahlmodul freie Wahl (alle Studiengänge), Wissenschaftliches Modul Multimediale Komposition Master