{"id":"https://openalex.org/W6968293534","doi":"https://doi.org/10.5281/zenodo.14877507","title":"SymPAC: Scalable Symbolic Music Generation With Prompts and Constraints","display_name":"SymPAC: Scalable Symbolic Music Generation With Prompts and Constraints","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6968293534","doi":"https://doi.org/10.5281/zenodo.14877507"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877507","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877507","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.14877507","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Haonan Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Haonan Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jordan B. L. Smith","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jordan B. L. Smith","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Janne Spijkervet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Janne Spijkervet","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ju-Chiang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ju-Chiang Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Pei Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pei Zou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Bochen Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bochen Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Qiuqiang Kong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiuqiang Kong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Xingjian Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingjian Du","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"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":0.41307678,"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":0.6383000016212463,"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":0.6383000016212463,"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":0.1445000022649765,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.03660000115633011,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5586000084877014},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5218999981880188},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.508400022983551},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4422000050544739},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.38029998540878296},{"id":"https://openalex.org/keywords/the-symbolic","display_name":"The Symbolic","score":0.3765000104904175},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.3691999912261963},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.35749998688697815}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.763700008392334},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5586000084877014},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5218999981880188},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.508400022983551},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40149998664855957},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C2776095079","wikidata":"https://www.wikidata.org/wiki/Q489538","display_name":"The Symbolic","level":2,"score":0.3765000104904175},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.3691999912261963},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3614000082015991},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.35749998688697815},{"id":"https://openalex.org/C47350684","wikidata":"https://www.wikidata.org/wiki/Q5157306","display_name":"Computational creativity","level":3,"score":0.3513000011444092},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.34709998965263367},{"id":"https://openalex.org/C65620979","wikidata":"https://www.wikidata.org/wiki/Q7661176","display_name":"Symbolic data analysis","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.30480000376701355},{"id":"https://openalex.org/C2779639559","wikidata":"https://www.wikidata.org/wiki/Q7661178","display_name":"Symbolic execution","level":3,"score":0.30399999022483826},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30300000309944153},{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2720000147819519},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C2776962539","wikidata":"https://www.wikidata.org/wiki/Q6472078","display_name":"Lagging","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877507","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877507","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.14877507","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877507","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":{"Progress":[0],"in":[1,19,117,147],"the":[2,23,34,64,72,76,91,94,136],"task":[3],"of":[4,22,25,37,66,78,93,140],"symbolic":[5,26,55,80],"music":[6,39,149],"generation":[7,81],"may":[8,144],"be":[9,145],"lagging":[10],"behind":[11],"other":[12],"tasks":[13],"like":[14],"audio":[15,38,86],"and":[16,57,106,119,138,154],"text":[17],"generation,":[18],"part":[20],"because":[21],"scarcity":[24],"training":[27,79],"data.":[28,87],"In":[29],"this":[30,69,141],"paper,":[31],"we":[32,97],"leverage":[33],"greater":[35],"scale":[36],"data":[40],"by":[41,112],"applying":[42],"pre-trained":[43],"MIR":[44],"models":[45,82],"(for":[46],"transcription,":[47],"beat":[48],"tracking,":[49],"structure":[50],"analysis,":[51],"etc.)":[52],"to":[53,74,89,152],"extract":[54],"events":[56],"encode":[58],"them":[59],"into":[60],"token":[61],"sequences.":[62],"To":[63],"best":[65],"our":[67],"knowledge,":[68],"work":[70],"is":[71,110],"first":[73],"demonstrate":[75],"feasibility":[77],"solely":[83],"from":[84],"auto-transcribed":[85],"Furthermore,":[88],"enhance":[90],"controllability":[92,139],"trained":[95],"model,":[96],"introduce":[98],"SymPAC":[99],"(Symbolic":[100],"Music":[101],"Language":[102],"Model":[103],"with":[104],"Prompting":[105],"Constrained":[107,124],"Generation),":[108],"which":[109,143],"distinguished":[111],"using":[113],"(a)":[114],"prompt":[115],"bars":[116],"encoding":[118],"(b)":[120],"a":[121],"technique":[122],"called":[123],"Generation":[125],"via":[126],"Finite":[127],"State":[128],"Machines":[129],"(FSMs)":[130],"during":[131],"inference":[132],"time.":[133],"We":[134],"show":[135],"flexibility":[137],"approach,":[142],"critical":[146],"making":[148],"AI":[150],"useful":[151],"creators":[153],"users.":[155]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}