{"id":"https://openalex.org/W6949599054","doi":"https://doi.org/10.5281/zenodo.14877447","title":"Content-Based Controls for Music Large Language Modeling","display_name":"Content-Based Controls for Music Large Language Modeling","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6949599054","doi":"https://doi.org/10.5281/zenodo.14877447"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877447","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877447","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.14877447","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Liwei Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liwei Lin","raw_affiliation_strings":[],"raw_orcid":null,"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":[],"raw_orcid":null,"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":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Yixiao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yixiao Zhang","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":0.43835616,"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/T11309","display_name":"Music and Audio Processing","score":0.6152999997138977,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.6152999997138977,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.12319999933242798,"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":0.06440000236034393,"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/chord","display_name":"Chord (peer-to-peer)","score":0.7748000025749207},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6446999907493591},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5602999925613403},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.5360999703407288},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.4846999943256378},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.3898000121116638},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.37869998812675476},{"id":"https://openalex.org/keywords/pop-music-automation","display_name":"Pop music automation","score":0.36250001192092896}],"concepts":[{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.7748000025749207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.711899995803833},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6446999907493591},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5602999925613403},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.5360999703407288},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5311999917030334},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.4846999943256378},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45249998569488525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4115000069141388},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3898000121116638},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C73520026","wikidata":"https://www.wikidata.org/wiki/Q7229091","display_name":"Pop music automation","level":4,"score":0.36250001192092896},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C195818886","wikidata":"https://www.wikidata.org/wiki/Q5421724","display_name":"Expressive power","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C114611597","wikidata":"https://www.wikidata.org/wiki/Q373342","display_name":"Popular music","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C143857728","wikidata":"https://www.wikidata.org/wiki/Q193544","display_name":"Music theory","level":3,"score":0.2669000029563904},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2619999945163727}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877447","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877447","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.14877447","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877447","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/4","score":0.6656669974327087,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"witnessed":[3],"a":[4,96,107,143],"rapid":[5],"growth":[6],"of":[7,14,22,37,138,168,173],"large-scale":[8],"language":[9,103],"models":[10,18,73],"in":[11],"the":[12,34,72,132,139,169],"domain":[13],"music":[15,41,50,81,101,124,191],"audio.":[16],"Such":[17],"enable":[19],"end-to-end":[20],"generation":[21,29,125,193],"higher-quality":[23],"music,":[24],"and":[25,57,65,76,87,164,184,194,199],"some":[26],"allow":[27],"conditioned":[28],"using":[30],"text":[31,38,185],"descriptions.":[32],"However,":[33],"control":[35,98],"power":[36],"controls":[39,78,183],"on":[40,79,142],"is":[42],"intrinsically":[43],"limited,":[44],"as":[45,55,63,84],"they":[46],"can":[47],"only":[48],"describe":[49],"indirectly":[51],"through":[52],"meta-data":[53],"(such":[54,62],"singers":[56],"instruments)":[58],"or":[59],"high-level":[60],"representations":[61],"genre":[64],"emotion).":[66],"We":[67,130,158],"aim":[68],"to":[69],"further":[70],"equip":[71],"with":[74,126,134,146],"direct":[75],"content-based":[77,97,156,182],"innate":[80],"languages":[82],"such":[83],"pitch,":[85],"chords":[86],"drum":[88],"track.":[89],"To":[90],"this":[91],"end,":[92],"we":[93,177],"contribute":[94],"Coco-Mulla,":[95],"method":[99,111],"for":[100,113],"large":[102],"modeling.":[104],"It":[105],"uses":[106],"parameter-efficient":[108],"fine-tuning":[109],"(PEFT)":[110],"tailored":[112],"Transformer-based":[114],"audio":[115],"models.":[116],"Experiments":[117],"show":[118,178],"that":[119,179],"our":[120,152,187],"approach":[121,153],"achieves":[122,189],"high-quality":[123],"low-resource":[127],"semi-supervised":[128],"learning.":[129],"fine-tune":[131],"model":[133],"less":[135],"than":[136,148],"4%":[137],"orignal":[140],"parameters":[141],"small":[144],"dataset":[145],"fewer":[147],"300":[149],"songs.":[150],"Moreover,":[151],"enables":[154],"effective":[155],"controls.":[157],"illustrate":[159],"its":[160],"controllability":[161],"via":[162],"chord":[163],"rhythm":[165],"conditions,":[166],"two":[167],"most":[170],"salient":[171],"features":[172],"pop":[174],"music.":[175],"Furthermore,":[176],"by":[180],"combining":[181],"descriptions,":[186],"system":[188],"flexible":[190],"variation":[192],"arrangement.":[195],"Our":[196],"source":[197],"codes":[198],"demos":[200],"are":[201],"available":[202],"online.":[203]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}