Skip to main content
Open Access Publications from the University of California

UC Santa Barbara

UC Santa Barbara Electronic Theses and Dissertations bannerUC Santa Barbara

Composing in Latent Space: Music Information Retrieval Driven Algorithmic Composition


The modern composer spends a large amount of time collecting and then sorting though digital audio files. There have been many attempts to make use of the field of Music Information Retrieval to organize and make use of the large databases of sound. This paper will present methods to both deal with large amounts of data and to harness that data for music creation itself. This document also showcases the compositional growth during the my studies at UCSB and the technical and aesthetic challenges that I had along the way.In this dissertation I will first layout the theory and history of work that has come before. I will then put my musical output in a greater musical context, explain my implementation of the theoretical concepts, presenting my own strategies, and specifically elaborating on the application of these techniques in two of my most recent compositions, Usynlig and A More Sound Output®.

Main Content
For improved accessibility of PDF content, download the file to your device.
Current View