{"id":"https://openalex.org/W6929995174","doi":"https://doi.org/10.5281/zenodo.10265265","title":"Polyffusion: A Diffusion Model for Polyphonic Score Generation With Internal and External Controls","display_name":"Polyffusion: A Diffusion Model for Polyphonic Score Generation With Internal and External Controls","publication_year":2023,"publication_date":"2023-11-04","ids":{"openalex":"https://openalex.org/W6929995174","doi":"https://doi.org/10.5281/zenodo.10265265"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10265265","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265265","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.10265265","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Lejun Min","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lejun Min","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Junyan Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junyan Jiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Gus Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gus Xia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Jingwei Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingwei Zhao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5088,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84931875,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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/T13399","display_name":"Unemployment and Economic Growth","score":0.012900000438094139,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13399","display_name":"Unemployment and Economic Growth","score":0.012900000438094139,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14093","display_name":"Global Health and Epidemiology","score":0.01119999960064888,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10467","display_name":"Psychometric Methodologies and Testing","score":0.010200000368058681,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.7483999729156494},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5378000140190125},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.41990000009536743},{"id":"https://openalex.org/keywords/harmony","display_name":"Harmony (Music)","score":0.4171000123023987},{"id":"https://openalex.org/keywords/internal-model","display_name":"Internal model","score":0.3971000015735626},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3962000012397766}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.7483999729156494},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6463000178337097},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5378000140190125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5224999785423279},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.41990000009536743},{"id":"https://openalex.org/C89721942","wikidata":"https://www.wikidata.org/wiki/Q184421","display_name":"Harmony (Music)","level":3,"score":0.4171000123023987},{"id":"https://openalex.org/C28427503","wikidata":"https://www.wikidata.org/wiki/Q13580300","display_name":"Internal model","level":3,"score":0.3971000015735626},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3962000012397766},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3416000008583069},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30070000886917114},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2671999931335449}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.10265265","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265265","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.10265265","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265265","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,90],"propose":[1],"Polyffusion,":[2],"a":[3,45,101],"diffusion":[4],"model":[5,20,54,73,133],"that":[6,92,131],"generates":[7],"polyphonic":[8],"music":[9,13,25,49,64,67,105,118,122],"scores":[10],"by":[11,93],"regarding":[12],"as":[14,80,146],"image-like":[15],"piano":[16],"roll":[17],"representations.":[18],"The":[19],"is":[21],"capable":[22],"of":[23,47,62,104],"controllable":[24],"generation":[26,65,110,114],"with":[27,74],"two":[28],"paradigms:":[29],"internal":[30,95],"control":[31,36,70],"and":[32,50,96,121,138,141],"external":[33,75,97,147],"control.":[34],"Internal":[35],"refers":[37],"to":[38,59],"the":[39,48,53,56,60,72,87],"process":[40],"in":[41],"which":[42],"users":[43],"pre-define":[44],"part":[46],"then":[51],"let":[52],"infill":[55],"rest,":[57],"similar":[58],"task":[61],"masked":[63],"(or":[66],"inpainting).":[68],"External":[69],"conditions":[71,148],"yet":[76],"related":[77],"information,":[78],"such":[79],"chord,":[81],"texture,":[82],"or":[83,126],"other":[84],"features,":[85],"via":[86],"cross-attention":[88],"mechanism.":[89],"show":[91,130],"using":[94,142],"controls,":[98],"Polyffusion":[99],"unifies":[100],"wide":[102],"range":[103],"creation":[106],"tasks,":[107],"including":[108],"melody":[109],"given":[111,115,124],"accompaniment,":[112],"accompaniment":[113],"melody,":[116],"arbitrary":[117],"segment":[119],"inpainting,":[120],"arrangement":[123],"chords":[125],"textures.":[127],"Experimental":[128],"results":[129],"our":[132],"significantly":[134],"outperforms":[135],"existing":[136],"transformer":[137],"sampling-based":[139],"baselines,":[140],"pre-trained":[143],"disentangled":[144],"representations":[145],"yields":[149],"more":[150],"effective":[151],"controls.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}
