@inproceedings{9c9f20af2a774a98a66a286fa2fe0a01,
title = "Interpreting Graphic Notation with MusicLDM: An AI Improvisation of Cornelius Cardew's Treatise",
abstract = "This work presents a novel method for composing and improvising music inspired by Cornelius Cardew's Treatise, using AI to bridge graphic notation and musical expression. By leveraging OpenAI's ChatGPT to interpret the abstract visual elements of Treatise, we convert these graphical images into descriptive textual prompts. These prompts are then input into MusicLDM, a pre-trained latent diffusion model designed for music generation. We introduce a technique called {"}outpainting,{"}which overlaps sections of AI-generated music to create a seamless and cohesive composition. We demostrate a new perspective on performing and interpreting graphic scores, showing how AI can transform visual stimuli into sound and expand the creative possibilities in contemporary/experimental music composition. Musical pieces are available at https://bit.ly/TreatiseAI.",
keywords = "ChatGPT, graphic notation, Musi-cLDM, Treatise",
author = "Tornike Karchkhadze and Keren Shao and Shlomo Dubnov",
note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 2024 IEEE International Conference on Big Data, BigData 2024 ; Conference date: 15-12-2024 Through 18-12-2024",
year = "2024",
month = jan,
day = "1",
doi = "10.1109/BigData62323.2024.10825824",
language = "English",
series = "Proceedings - 2024 IEEE International Conference on Big Data, BigData 2024",
publisher = "Institute of Electrical and Electronics Engineers",
pages = "3181--3190",
editor = "Wei Ding and Chang-Tien Lu and Fusheng Wang and Liping Di and Kesheng Wu and Jun Huan and Raghu Nambiar and Jundong Li and Filip Ilievski and Ricardo Baeza-Yates and Xiaohua Hu",
booktitle = "Proceedings - 2024 IEEE International Conference on Big Data, BigData 2024",
address = "United States",
}