[-] Show simple item record

dc.contributor.advisorDerakhshani, Reza
dc.contributor.authorMiles, Samuel Alan
dc.date.issued2023
dc.date.submitted2023 Summer
dc.descriptionTitle from PDF of title page, viewed September 6, 2023
dc.descriptionThesis advisor: Reza Derakhshani
dc.descriptionVita
dc.descriptionIncludes bibliographical references (pages 37-41)
dc.descriptionThesis (M.S.)--Department of Computer Science and Electrical Engineering. University of Missouri--Kansas City, 2023
dc.description.abstractGenerative AI systems are of great interest in the field of automated music production. Current well-known state-of-the-art music generation systems such as MusicLM, while incredibly versatile and tractable, do not allow for direct control of tone or texture of the generated instruments other than by altering the text prompt, which also alters the structure of the generated composition. Therefore, symbolic music generation would still be of great use to musicians. Using current state-of-the-art advancements in Deep Learning and an off-the-shelf MIDI dataset and pretrained English encoder, this work proposes a novel sequence-to-sequence music generation model that converts written descriptions of the style and artistic themes of a song into coherent MIDI musical representations. The architecture and synthetic dataset used in training this model were constructed with special consideration to the needs of musicians, namely, a native musical format, lack of association between any particular artist and musical style, and the possibility of live usage with a human accompaniment.
dc.description.tableofcontentsIntroduction -- Background and related work -- Methodology -- Results and discussion -- Conclusion
dc.format.extentv, 42 pages
dc.identifier.urihttps://hdl.handle.net/10355/96469
dc.subject.lcshComputer composition (Music)
dc.subject.otherThesis -- University of Missouri--Kansas City -- Electrical and Computer Engineering
dc.titleA Multimodal Text-To-MIDI Transformer Model with Special Consideration To Artist Usage
thesis.degree.disciplineElectrical and Computer Engineering (UMKC)
thesis.degree.grantorUniversity of Missouri--Kansas City
thesis.degree.levelMasters
thesis.degree.nameM.S. (Master of Science)


Files in this item

Thumbnail
[PDF]

This item appears in the following Collection(s)

[-] Show simple item record