Abstract
In recent decades the live music performance and DJ industry has undergone a transition from analog to digital music being the norm. Audio analysis and mixing software is now a necessity for modern DJs and their preferred equipment. However, it still stands that DJs must thoroughly learn their tracks and decide which transition well together in order to produce a smooth mix. This project looks at how machine learning-based systems can aid DJs in this process; it raises questions about the use of artificial intelligence within a heavily subjective form of live performance, and its potential effectiveness in this field. This project will also assess the nature of varying electronic genres and how they affect one another. Preliminary research will be conducted to assess how musical genre is determined, and how machine learning can utilize track features provided by Spotify research data to predict genres of electronic music. A KNN-based electronic genre prediction system will be developed from this, and its capabilities assessed.
Keywords
Artificial Intelligence, Machine Learning, Digital Music, Electronic Music
Document Type
Thesis
Publication Date
2023
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Recommended Citation
Fellenor, N. (2023) Artificial Intelligence Incorporated into Audio Analysis of Electronic Music. Thesis. University of Plymouth. Retrieved from https://pearl.plymouth.ac.uk/sc-theses/54
