Page 133 - Weiss, Jernej, ur./ed. 2025. Glasbena interpretacija: med umetniškim in znanstvenim┊Music Interpretation: Between the Artistic and the Scientific. Koper/Ljubljana: Založba Univerze na Primorskem in Festival Ljubljana. Studia musicologica Labacensia, 8

Weiss, Jernej, ur. 2025. Glasbena interpretacija: med umetniškim in znanstvenim | Music Interpretation: Between the Artistic and the Scientific.
Koper/Ljubljana: Založba Univerze na Primorskem in Festival Ljubljana. https://doi.org/10.26493/978-961-293-425-5.133-146
© 2025 Wolfgang Marx

AI and Musical Interpretation

Wolfgang Marx
Univerzitetni kolidž v Dublinu
University College Dublin

Introduction
It was only a question of time until generative artificial intelligence (AI)
would move on from creating texts and pictures to the creation of music.
While general AI content generators are expanding more and more into
the music area, there are now also more and more music-specific generative
1
2
3
AI systems such as Udio, Soundraw and DeepAI Music Generator. Many
of them are accessible for free, although using the full range of capabilities
usually requires signing up for a paid subscription. What is the potential
impact of AI-generated music on questions of musical interpretation? My
argument will be developed in three steps: firstly, a number of examples of
AI-generated songs are presented in order to outline what AI can do at the
moment. Secondly, the way in which large language models (LLMs) – the
underlying systems of many AI generators – work is discussed, showing
that LLMs have a tendency to standardise their results, while also remov-
ing any quirk or idiosyncrasy that human creators would (unconsciously)
include. AI outputs are “depersonalised”, as it were. Thirdly, the concept
of “model collapse” is introduced. It leads to further homogenisation as AI
systems will inevitably include more and more data in their processes that
are already AI-created, setting in motion a spiral of self-referentiality that
1 Udio Beta, https://www.udio.com/.
2 Soundraw, https://soundraw.io/.
3 Deep AI Music Generator, https://deepai.org/music.

133