Deep Learning Assisted Music Composition

dc.contributor.advisorJin, Yufang
dc.contributor.authorRanjbar, Sorush
dc.contributor.committeeMemberHuang, Yufei
dc.contributor.committeeMemberZhang, Michelle
dc.creator.orcidhttps://orcid.org/0000-0003-3859-4425
dc.date.accessioned2024-02-12T19:52:42Z
dc.date.available2024-02-12T19:52:42Z
dc.date.issued2019
dc.descriptionThis item is available only to currently enrolled UTSA students, faculty or staff. To download, navigate to Log In in the top right-hand corner of this screen, then select Log in with my UTSA ID.
dc.description.abstractMuch headway has been made over the last 70 years in the field of deep learning, opening new doors for music composers. The potential for deep learning models as assistive tools, rather than end to end music composers, is reviewed here. Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Deep Convolutional Generative Adversarial Networks (DC-GAN) are trained with symbolic music data with the goal of producing segments of interesting music. These musical motifs are qualitatively compared to identify which model could function as a musical creative block mitigator. The model that generates the most interesting harmonic content is chosen as the starting point for a progressive rock composition. The three models are trained over Musical Instrument Digital Interface (MIDI) files, a format which is used to digitally represent musical notes by integers. The main challenge in this thesis presented itself during the training process, where the recurrent models experienced overfitting. This challenge can be overcome by reducing the model complexity and ensuring that the training data arises from the same pool as the validation data. Despite overfitting, the LSTM music did not mimic the training data and had many phrases which were unique. The DC-GAN generated sample inspired the creation of a 2-minute song in less than 20 minutes. The use of deep learning tools to inspire original music composition is achievable and can be used to remedy the temporary creative blocks that musicians face.
dc.description.departmentElectrical and Computer Engineering
dc.format.extent52 pages
dc.format.mimetypeapplication/pdf
dc.identifier.isbn9781392676448
dc.identifier.urihttps://hdl.handle.net/20.500.12588/5238
dc.languageen
dc.subjectDeep Learning
dc.subjectGenerative Adversarial Networks
dc.subjectLong Short Term Memory
dc.subjectMachine Learning
dc.subjectMusic Information Technology
dc.subject.classificationElectrical engineering
dc.subject.classificationComputer science
dc.subject.lcshComposition (Music) -- Instruction and study
dc.titleDeep Learning Assisted Music Composition
dc.typeThesis
dc.type.dcmiText
dcterms.accessRightspq_closed
thesis.degree.departmentElectrical and Computer Engineering
thesis.degree.grantorUniversity of Texas at San Antonio
thesis.degree.levelMasters
thesis.degree.nameMaster of Science

Files

Original bundle

Now showing 1 - 3 of 3
No Thumbnail Available
Name:
Ranjbar_utsa_1283M_12973.pdf
Size:
2.17 MB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
gan_86000_sample.wav
Size:
3.18 MB
Format:
Broadcase Wave Format
No Thumbnail Available
Name:
GAN into Music-1.wav
Size:
13.4 MB
Format:
Broadcase Wave Format