Thesis Format
Monograph
Degree
Doctor of Philosophy
Program
Music
Supervisor
Frehner, Paul
2nd Supervisor
Turkel, William J.
Abstract
Creating an artificial intelligence aid for music composers requires a practical and modular approach that allows the composer to manipulate the technology as needed in the search for new sounds and ideas. Many existing approaches fail to capture the interest of composers as they are limited beyond their demonstrative purposes or allow minimal interaction with the composer. Score-Transformer (ST) demonstrates a practical integration of artificial intelligence to aid in the creation of new music by working seamlessly alongside any popular notation software. Furthermore, ST can be trained by the user with additional works (including their own compositions), fine-tuning it and minimizing the risk of the software becoming outdated or impractical for continued use. ST was used in the creation of my dissertation piece, Music for Self-Attention.
Music for Self-Attention features an innovative algorithmic approach to traditional compositional methods by demonstrating the benefits of using deep learning in music composition to aid with certain pitch and rhythmic decisions. These artificially generated decisions were not intended to fully remove the human element from composing but rather to work in tandem with the composer, in this case, myself. The piece lasts approximately 23 minutes and loosely follows a form of theme and variations in reverse. This steady process gradually deconstructs a series of variations which were each was initially generated by artificial means until the final movement—containing no artificial intervention—is revealed. This is not a theme and variations in the usual way as the listener won’t hear the theme in each variation. Each movement reflects different processes involved in the training and deployment of artificially intelligent software. Music for Self-Attention is meant to demonstrate a symbiotic relationship that can exist between artificial and human creativity in music composition.
Summary for Lay Audience
Artificial intelligence has more recently been permeating our everyday lives through applications such as personal assistants (Apple’s Siri or Amazon Alexa), search, video, and product recommendation (Google, Youtube, etc.) and has even been used to beat human champions at popular games such as Go and Chess. Therefore, it seemed as though music composition could similarly benefit from artificially intelligent software to aid in the creation of new music. Some attempts had been made in the past, but many failed to capture the interest of composers as they could be limited beyond demonstrative purposes or allow minimal interaction with the composer. Score-Transformer (ST) is an artificially intelligent software that can be used to aid in the creation of new music by working seamlessly alongside any popular notation software. Furthermore, ST can be fed additional works (including the user’s own compositions) in order to update it, minimizing the risk of the software becoming outdated or impractical for continued use. ST was used in the creation of my dissertation piece, Music for Self-Attention.
Music for Self-Attention features an innovative approach to traditional compositional methods by demonstrating the benefits of artificial intelligence used to aid with certain pitch and rhythmic decisions when developing the score. The use of artificial intelligence was not intended to replace the composer in creating new music, but rather to work alongside the composer and make suggestions. The piece, for string quartet, is in six movements and lasts approximately 23 minutes. Each movement of the piece features music that was initially generated by artificial means until the final movement which did not use Score-Transformer. Music for Self-Attention is meant to demonstrate a relationship that can exist between artificial and human creativity in music composition.
Recommended Citation
Lupker, Jeffrey A T, "Music for Self-Attention" (2021). Electronic Thesis and Dissertation Repository. 7898.
https://ir.lib.uwo.ca/etd/7898
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.