{"id":"https://openalex.org/W6930731897","doi":"https://doi.org/10.5281/zenodo.14877337","title":"MusiConGen: Rhythm and Chord Control for Transformer-Based Text-to-Music Generation","display_name":"MusiConGen: Rhythm and Chord Control for Transformer-Based Text-to-Music Generation","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6930731897","doi":"https://doi.org/10.5281/zenodo.14877337"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877337","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877337","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":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.14877337","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yun-Han Lan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yun-Han Lan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wen-Yi Hsiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen-Yi Hsiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hao-Chung Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao-Chung Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Yi-Hsuan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.66484597,"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/T11518","display_name":"Cervical and Thoracic Myelopathy","score":0.0877000018954277,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11518","display_name":"Cervical and Thoracic Myelopathy","score":0.0877000018954277,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10618","display_name":"Aortic Disease and Treatment Approaches","score":0.0674000009894371,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10420","display_name":"Intracranial Aneurysms: Treatment and Complications","score":0.06639999896287918,"subfield":{"id":"https://openalex.org/subfields/2728","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/chord","display_name":"Chord (peer-to-peer)","score":0.9010999798774719},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.8046000003814697},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.41760000586509705},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.3813999891281128},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.37529999017715454},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.32519999146461487}],"concepts":[{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.9010999798774719},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.8046000003814697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7038999795913696},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6668999791145325},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3677000105381012},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.32519999146461487},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3003000020980835},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.2996000051498413},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.27390000224113464},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26019999384880066},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2581999897956848}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877337","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877337","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":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.14877337","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877337","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":"ConferencePaper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5239142179489136}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"text-to-music":[1,39],"models":[2],"can":[3,74,113],"produce":[4],"high-quality":[5],"audio":[6,83,135],"with":[7,122],"great":[8],"diversity.":[9],"However,":[10],"textual":[11,93],"prompts":[12],"alone":[13],"cannot":[14],"precisely":[15],"control":[16],"temporal":[17],"musical":[18,77],"features":[19,78,104],"such":[20],"as":[21,66],"chords":[22,65],"and":[23,64,92,105,130,133],"rhythm":[24,63],"of":[25],"the":[26,44,67,72,106,123,128],"generated":[27],"music.":[28],"To":[29],"address":[30],"this":[31],"challenge,":[32],"we":[33],"introduce":[34],"MusiConGen,":[35],"a":[36,81],"temporallyconditioned":[37],"Transformer-based":[38],"model":[40,131],"that":[41,60,111,119],"builds":[42],"upon":[43],"pretrained":[45],"MusicGen":[46],"framework.":[47],"Our":[48,95],"innovation":[49],"lies":[50],"in":[51],"an":[52],"efficient":[53],"finetuning":[54],"mechanism,":[55],"tailored":[56],"for":[57],"consumer-grade":[58],"GPUs,":[59],"integrates":[61],"automaticallyextracted":[62],"condition":[68,73],"signal.":[69],"During":[70],"inference,":[71],"either":[75],"be":[76,86],"extracted":[79,103],"from":[80,102,108],"reference":[82],"signal,":[84],"or":[85],"user-defined":[87],"symbolic":[88],"chord":[89],"sequence,":[90],"BPM,":[91],"prompts.":[94],"performance":[96],"evaluation":[97],"on":[98],"two":[99],"datasets\u2014one":[100],"derived":[101],"other":[107],"user-created":[109],"inputs\u2014demonstrates":[110],"MusiConGen":[112],"generate":[114],"realistic":[115],"backing":[116],"track":[117],"music":[118],"aligns":[120],"well":[121],"specified":[124],"conditions.":[125],"We":[126],"open-source":[127],"code":[129],"checkpoints,":[132],"provide":[134],"examples":[136],"online,":[137],"https://musicongen.github.io/musicongen_demo/.":[138]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}