[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128674-en":3,"doc-seo-128674-105":31,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128674,962084928432,"Emma Wilson","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","From Notes to Musical Form - A Machine Learning Approach","From Notes to Musical Form: A Machine Learning Approach develops methods for generating and shaping musical outputs using modern machine learning models. The work surveys ML music generation, data representations, and applications such as transcription, co-composition, music production, and synthetic instruments. It then examines diffusion models and conditional sampling, before addressing large language model techniques for producing controllable musical forms, including evaluation strategies and meta-optimization. Dimensionality reduction methods support representation learning across experiments.","UC San Diego  \nUC San Diego Electronic Theses and Dissertations  \nTitle  \nFrom Notes to Musical Form: A Machine Learning Approach  \nPermalink  \n[https://escholarship.org/uc/item/0w95n1j0](https://escholarship.org/uc/item/0w95n1j0)  \nAuthor  \nAtassi, Lilac  \nPublication Date  \n2024  \nPeer reviewed|Thesis/dissertation  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nUNIVERSITY OF CALIFORNIA SAN DIEGO  \nFrom Notes to Musical Form: A Machine Learning Approach  \nA dissertation submitted in partial satisfaction of the requirements for the degree Doctor of Philosophy  \nin  \nMusic  \nby  \nLilac Atassi  \nCommittee in charge:  \nProfessor Shahrokh Yadegari, Chair  \nProfessor Garrison W. Cottrell  \nProfessor Thomas Erbe  \nProfessor Miller S. Puckette  \nProfessor Robert Wannamaker  \nCopyright Lilac Atassi, 2024 All rights reserved.  \nThe Dissertation of Lilac Atassi is approved, and it is acceptable in quality and form for publication on microfilm and electronically.  \nUniversity of California San Diego  \n2024  \nTABLE OF CONTENTS  \nDissertation Approval Page .................................................... iii  \nTable of Contents ............................................................ iv  \nList of Figures ............................................................... vii  \nAcknowledgements ........................................................... xii  \nVita ........................................................................ xiii  \nAbstract of the Dissertation .................................................... xiv  \nChapter 1 Introduction ..................................................... 1  \nChapter 2 ML Music Generation ............................................ 4  \n2.1 Abstract ............................................................. 4  \n2.2 Introduction ......................................................... 4  \n2.3 Data ................................................................ 9  \n2.3.1 Data representation ............................................ 9  \n2.3.2 Publicly available data .......................................... 11  \n2.4 Applications ......................................................... 12  \n2.4.1 Music transcription ............................................ 13  \n2.4.2 Co-composition ............................................... 13  \n2.4.3 Music production .............................................. 15  \n2.4.4 Synthetic Instrument ........................................... 16  \n2.5 Models and network architectures ....................................... 16  \n2.5.1 Feedforward networks .......................................... 16  \n2.5.2 Recurrent networks ............................................ 20  \n2.5.3 Generative adversarial networks .................................. 21  \n2.5.4 Autoencoders ................................................. 22  \n2.5.5 Transformers .................................................. 23  \n2.5.6 Diffusion ..................................................... 25  \n2.6 Training methods ..................................................... 26  \n2.6.1 Optimization .................................................. 27  \n2.6.2 Autoregressive order ........................................... 30  \n2.7 Evaluation approaches ................................................ 30  \n2.8 Beyond statistical models .............................................. 32  \n2.9 Experiments with diffusion ............................................ 35  \n2.10 Conclusions ......................................................... 38  \nChapter 3 Diffusion Models ................................................ 41  \n3.1 Abstract ............................................................. 41  \n3.2 Introduction ......................................................... 41  \n3.3 Deep Unsupervised Learning using Nonequilibrium Thermodynamics ........ 43  \n3.4 Modern Diffusion Models .........................","cbCaiqAxmtAk78Lz","https://ap.wps.com/l/cbCaiqAxmtAk78Lz","pdf",21536509,4,1,168,"English","en",105,"# Chapter 1 Introduction\n# Chapter 2 ML Music Generation\n## Data\n## Applications\n## Models and network architectures\n## Training methods\n## Evaluation approaches\n## Experiments with diffusion\n# Chapter 3 Diffusion Models\n## Deep Unsupervised Learning using Nonequilibrium Thermodynamics\n## Modern Diffusion Models\n## Conditional sampling and latent space\n## Experiments\n# Chapter 4 Large Language Models: From Notes to Musical Form\n## Unlearnable Musical Form\n## EnCodec and MusicGen\n## Controlling MusicGen by a Language Model\n## Evaluation\n## Meta Optimization by LLM\n# Chapter 5 Dimensionality Reduction\n## Dimensionality reduction algorithms","[{\"question\":\"What topics are covered in ML music generation?\",\"answer\":\"The document covers data representations, applications (transcription, co-composition, production, synthetic instruments), model families (feedforward, recurrent, GANs, autoencoders, transformers, diffusion), training methods, and evaluation approaches.\"},{\"question\":\"How do diffusion models fit into the research?\",\"answer\":\"Diffusion models are introduced as a core method, including deep unsupervised learning with nonequilibrium thermodynamics, conditional sampling and latent-space concepts, and dedicated experimental sections.\"},{\"question\":\"How are large language models used to control musical output?\",\"answer\":\"The research proposes controlling MusicGen using a language model, and includes multiple evaluation methods plus meta-optimization by LLM to improve the musical form and results.\"}]","From Notes to Musical Form - A Machine Learning Approach | PDF",1786002487,423,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"from-notes-to-musical-form-a-machine-learning-approach","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":20},"https://docshare.wps.com/document/from-notes-to-musical-form-a-machine-learning-approach/128674/",{"url":53,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-25","2026-08-06",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What topics are covered in ML music generation?","Question",{"text":76,"@type":77},"The document covers data representations, applications (transcription, co-composition, production, synthetic instruments), model families (feedforward, recurrent, GANs, autoencoders, transformers, diffusion), training methods, and evaluation approaches.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How do diffusion models fit into the research?",{"text":81,"@type":77},"Diffusion models are introduced as a core method, including deep unsupervised learning with nonequilibrium thermodynamics, conditional sampling and latent-space concepts, and dedicated experimental sections.",{"name":83,"@type":74,"acceptedAnswer":84},"How are large language models used to control musical output?",{"text":85,"@type":77},"The research proposes controlling MusicGen using a language model, and includes multiple evaluation methods plus meta-optimization by LLM to improve the musical form and results.","https://schema.org",{"og:url":53,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]