{"id":"https://openalex.org/W6949772811","doi":"https://doi.org/10.5281/zenodo.14877365","title":"Long-Form Music Generation With Latent Diffusion","display_name":"Long-Form Music Generation With Latent Diffusion","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6949772811","doi":"https://doi.org/10.5281/zenodo.14877365"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877365","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877365","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.14877365","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zach Evans","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zach Evans","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Julian D. Parker","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julian D. Parker","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"CJ Carr","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"CJ Carr","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zachary Zukowski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zachary Zukowski","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Josiah Taylor","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Josiah Taylor","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Jordi Pons","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jordi Pons","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40010214,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.7695000171661377,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.7695000171661377,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.10140000283718109,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.023099999874830246,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.679099977016449},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.656000018119812},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5692999958992004},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.4787999987602234},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.45989999175071716},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.3206000030040741}],"concepts":[{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.679099977016449},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.656000018119812},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5692999958992004},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5375999808311462},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48809999227523804},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.4787999987602234},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.45989999175071716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4528000056743622},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C178884764","wikidata":"https://www.wikidata.org/wiki/Q510293","display_name":"Musical acoustics","level":3,"score":0.2856000065803528},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26269999146461487},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2574999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877365","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877365","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.14877365","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877365","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Audio-based":[0],"generative":[1,34],"models":[2],"for":[3],"music":[4,19,46,91],"have":[5,13],"seen":[6],"great":[7],"strides":[8],"recently,":[9],"but":[10],"so":[11],"far":[12],"not":[14],"managed":[15],"to":[16,43,49,75],"produce":[17,44],"full-length":[18,90],"tracks":[20],"with":[21,92],"coherent":[22,93],"musical":[23],"structure":[24],"from":[25],"text":[26],"prompts.":[27],"We":[28],"show":[29],"that":[30,87],"by":[31],"training":[32],"a":[33,56,60],"model":[35,53],"on":[36,59,77],"long":[37],"temporal":[38],"contexts":[39],"it":[40,88],"is":[41],"possible":[42],"long-form":[45],"of":[47,55,68],"up":[48],"4m":[50],"45s.":[51],"Our":[52],"consists":[54],"diffusion-transformer":[57],"operating":[58],"highly":[61],"downsampled":[62],"continuous":[63],"latent":[64],"representation":[65],"(latent":[66],"rate":[67],"21.5Hz).":[69],"It":[70],"obtains":[71],"state-of-the-art":[72],"generations":[73],"according":[74],"metrics":[76],"audio":[78],"quality":[79],"and":[80,83],"prompt":[81],"alignment,":[82],"subjective":[84],"tests":[85],"reveal":[86],"produces":[89],"structure.":[94]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}