VTechWorks staff will be away for the Independence Day holiday from July 4-7. We will respond to email inquiries on Monday, July 8. Thank you for your patience.
 

Latent Walking Techniques for Conditioning GAN-Generated Music

Simple item page
dc.contributor.authorEisenbeiser, Logan Ryanen
dc.contributor.committeechairGerdes, Ryan M.en
dc.contributor.committeechairFreeman, Laura J.en
dc.contributor.committeememberWang, Yue J.en
dc.contributor.departmentElectrical and Computer Engineeringen
dc.date.accessioned2020-09-22T08:00:42Zen
dc.date.available2020-09-22T08:00:42Zen
dc.date.issued2020-09-21en
dc.description.abstractArtificial music generation is a rapidly developing field focused on the complex task of creating neural networks that can produce realistic-sounding music. Generating music is very difficult; components like long and short term structure present time complexity, which can be difficult for neural networks to capture. Additionally, the acoustics of musical features like harmonies and chords, as well as timbre and instrumentation require complex representations for a network to accurately generate them. Various techniques for both music representation and network architecture have been used in the past decade to address these challenges in music generation. The focus of this thesis extends beyond generating music to the challenge of controlling and/or conditioning that generation. Conditional generation involves an additional piece or pieces of information which are input to the generator and constrain aspects of the results. Conditioning can be used to specify a tempo for the generated song, increase the density of notes, or even change the genre. Latent walking is one of the most popular techniques in conditional image generation, but its effectiveness on music-domain generation is largely unexplored. This paper focuses on latent walking techniques for conditioning the music generation network MuseGAN and examines the impact of this conditioning on the generated music.en
dc.description.abstractgeneralArtificial music generation is a rapidly developing field focused on the complex task of creating neural networks that can produce realistic-sounding music. Beyond simply generating music lies the challenge of controlling or conditioning that generation. Conditional generation can be used to specify a tempo for the generated song, increase the density of notes, or even change the genre. Latent walking is one of the most popular techniques in conditional image generation, but its effectiveness on music-domain generation is largely unexplored, especially for generative adversarial networks (GANs). This paper focuses on latent walking techniques for conditioning the music generation network MuseGAN and examines the impact and effectiveness of this conditioning on the generated music.en
dc.description.degreeMaster of Scienceen
dc.format.mediumETDen
dc.identifier.othervt_gsexam:27353en
dc.identifier.urihttp://hdl.handle.net/10919/100052en
dc.publisherVirginia Techen
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subjectMusic Generationen
dc.subjectLatent Walkingen
dc.subjectConditional Generationen
dc.subjectGenerative Adversarial Networken
dc.titleLatent Walking Techniques for Conditioning GAN-Generated Musicen
dc.typeThesisen
thesis.degree.disciplineComputer Engineeringen
thesis.degree.grantorVirginia Polytechnic Institute and State Universityen
thesis.degree.levelmastersen
thesis.degree.nameMaster of Scienceen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Eisenbeiser_LR_T_2020.pdf
Size:
10.08 MB
Format:
Adobe Portable Document Format
Download

Collections

Masters Theses