{"id":"https://openalex.org/W6947889277","doi":"https://doi.org/10.48550/arxiv.2503.19611","title":"Analyzable Chain-of-Musical-Thought Prompting for High-Fidelity Music Generation","display_name":"Analyzable Chain-of-Musical-Thought Prompting for High-Fidelity Music Generation","publication_year":2025,"publication_date":"2025-03-25","ids":{"openalex":"https://openalex.org/W6947889277","doi":"https://doi.org/10.48550/arxiv.2503.19611"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2503.19611","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.19611","pdf_url":"https://arxiv.org/pdf/2503.19611","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.19611","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Lam, Max W. Y.","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lam, Max W. Y.","raw_affiliation_strings":["Kunlun Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunlun Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xing, Yijin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xing, Yijin","raw_affiliation_strings":["Kunlun Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunlun Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071912411","display_name":"Weiya You","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"You, Weiya","raw_affiliation_strings":["Kunlun Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunlun Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wu, Jingcheng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Jingcheng","raw_affiliation_strings":["Kunlun Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunlun Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yin, Zongyu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Zongyu","raw_affiliation_strings":["Kunlun Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunlun Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiang, Fuqiang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Fuqiang","raw_affiliation_strings":["Kunlun Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunlun Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liu, Hangyu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Hangyu","raw_affiliation_strings":["Kunlun Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunlun Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liu, Feng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Feng","raw_affiliation_strings":["Kunlun Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunlun Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Xingda","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xingda","raw_affiliation_strings":["Kunlun Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunlun Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lu, Wei-Tsung","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Wei-Tsung","raw_affiliation_strings":["Kunlun Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunlun Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chen, Hanyu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Hanyu","raw_affiliation_strings":["Kunlun Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunlun Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Feng, Tong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Tong","raw_affiliation_strings":["Kunlun Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunlun Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhao, Tianwei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Tianwei","raw_affiliation_strings":["Kunlun Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunlun Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liu, Chien-Hung","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Chien-Hung","raw_affiliation_strings":["Kunlun Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunlun Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104098658","display_name":"Xuchen Song","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Xuchen","raw_affiliation_strings":["Kunlun Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunlun Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yang","raw_affiliation_strings":["Kunlun Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunlun Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123648620","display_name":"Yahui Zhou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yahui","raw_affiliation_strings":["Kunlun Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunlun Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":null,"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":0.8676999807357788,"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":0.8676999807357788,"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":0.1264999955892563,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.00139999995008111,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/music-generation","display_name":"music generation","score":0.843999981880188},{"id":"https://openalex.org/keywords/chain-of-thought-prompting","display_name":"chain-of-thought prompting","score":0.9959999918937683},{"id":"https://openalex.org/keywords/autoregressive-models","display_name":"autoregressive models","score":0.7960000038146973},{"id":"https://openalex.org/keywords/music-structure","display_name":"music structure","score":0.36000001430511475},{"id":"https://openalex.org/keywords/clap","display_name":"CLAP","score":0.5690000057220459},{"id":"https://openalex.org/keywords/instrumental-arrangements","display_name":"instrumental arrangements","score":0.5830000042915344},{"id":"https://openalex.org/keywords/music-copying","display_name":"music copying","score":0.4320000112056732},{"id":"https://openalex.org/keywords/musicality","display_name":"musicality","score":0.4059999883174896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7896999716758728},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5659000277519226},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5223000049591064},{"id":"https://openalex.org/C2779151265","wikidata":"https://www.wikidata.org/wiki/Q1156791","display_name":"Copying","level":2,"score":0.49149999022483826},{"id":"https://openalex.org/C11012388","wikidata":"https://www.wikidata.org/wiki/Q170658","display_name":"Creativity","level":2,"score":0.46219998598098755},{"id":"https://openalex.org/C73520026","wikidata":"https://www.wikidata.org/wiki/Q7229091","display_name":"Pop music automation","level":4,"score":0.4375},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41780000925064087},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3452000021934509},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C47350684","wikidata":"https://www.wikidata.org/wiki/Q5157306","display_name":"Computational creativity","level":3,"score":0.3084999918937683},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.2865000069141388},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2833000123500824},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28110000491142273},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.2752000093460083},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2503.19611","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.19611","pdf_url":"https://arxiv.org/pdf/2503.19611","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.19611","doi":"https://doi.org/10.48550/arxiv.2503.19611","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.19611","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.19611","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.19611","pdf_url":"https://arxiv.org/pdf/2503.19611","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6947889277.pdf","grobid_xml":"https://content.openalex.org/works/W6947889277.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W2971458685","https://openalex.org/W3021164770","https://openalex.org/W3097777922","https://openalex.org/W4221159371","https://openalex.org/W4221161695","https://openalex.org/W4288099666","https://openalex.org/W4292419534","https://openalex.org/W4293575120","https://openalex.org/W4297808394","https://openalex.org/W4300980117","https://openalex.org/W4306808908","https://openalex.org/W4318351475","https://openalex.org/W4318718630","https://openalex.org/W4318752004","https://openalex.org/W4319165821","https://openalex.org/W4319989813","https://openalex.org/W4322718191","https://openalex.org/W4323066695","https://openalex.org/W4327810158","https://openalex.org/W4399425629","https://openalex.org/W4400518537","https://openalex.org/W4401306886","https://openalex.org/W4403746926","https://openalex.org/W4405254469","https://openalex.org/W4405766390","https://openalex.org/W4407310319","https://openalex.org/W4407368670","https://openalex.org/W4409362462","https://openalex.org/W4412945359","https://openalex.org/W4414281281","https://openalex.org/W4414578659","https://openalex.org/W4415085369"],"related_works":["https://openalex.org/W7133229781","https://openalex.org/W7115740031","https://openalex.org/W4416519523","https://openalex.org/W2887720658","https://openalex.org/W4415080904","https://openalex.org/W7168244304","https://openalex.org/W7171706727","https://openalex.org/W4406233846","https://openalex.org/W6979226722","https://openalex.org/W7166889606"],"abstract_inverted_index":{"Autoregressive":[0],"(AR)":[1],"models":[2,19],"have":[3],"demonstrated":[4],"impressive":[5],"capabilities":[6],"in":[7,17,28,104],"generating":[8,68],"high-fidelity":[9],"music.":[10],"However,":[11],"the":[12,24,33,57,73,78,83],"conventional":[13,107],"next-token":[14],"prediction":[15],"paradigm":[16],"AR":[18,58],"does":[20],"not":[21],"align":[22],"with":[23],"human":[25],"creative":[26],"process":[27],"music":[29,53,65,117,125,151,170],"composition,":[30],"potentially":[31],"compromising":[32],"musicality":[34],"of":[35,77,93,101,116],"generated":[36],"samples.":[37],"To":[38],"overcome":[39],"this":[40],"limitation,":[41],"we":[42,89],"introduce":[43],"MusiCoT,":[44],"a":[45,91,146],"novel":[46],"chain-of-thought":[47],"(CoT)":[48],"prompting":[49],"technique":[50],"tailored":[51],"for":[52,113,150],"generation.":[54],"MusiCoT":[55,97,111,144,158],"empowers":[56],"model":[59],"to":[60,106],"first":[61],"outline":[62],"an":[63],"overall":[64],"structure":[66],"before":[67],"audio":[69,130],"tokens,":[70],"thereby":[71],"enhancing":[72],"coherence":[74],"and":[75,99,123,166],"creativity":[76],"resulting":[79],"compositions.":[80],"By":[81],"leveraging":[82],"contrastive":[84],"language-audio":[85],"pretraining":[86],"(CLAP)":[87],"model,":[88],"establish":[90],"chain":[92],"\"musical":[94],"thoughts\",":[95],"making":[96],"scalable":[98],"independent":[100],"human-labeled":[102],"data,":[103],"contrast":[105],"CoT":[108],"methods.":[109],"Moreover,":[110],"allows":[112],"in-depth":[114],"analysis":[115],"structure,":[118],"such":[119],"as":[120,132,145],"instrumental":[121],"arrangements,":[122],"supports":[124],"referencing":[126],"--":[127],"accepting":[128],"variable-length":[129],"inputs":[131],"optional":[133],"style":[134],"references.":[135],"This":[136],"innovative":[137],"approach":[138],"effectively":[139],"addresses":[140],"copying":[141],"issues,":[142],"positioning":[143],"vital":[147],"practical":[148],"method":[149],"prompting.":[152],"Our":[153,177],"experimental":[154],"results":[155],"indicate":[156],"that":[157,172],"consistently":[159],"achieves":[160],"superior":[161],"performance":[162],"across":[163],"both":[164],"objective":[165],"subjective":[167],"metrics,":[168],"producing":[169],"quality":[171],"rivals":[173],"state-of-the-art":[174],"generation":[175],"models.":[176],"samples":[178],"are":[179],"available":[180],"at":[181],"https://MusiCoT.github.io/.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":15},{"year":2025,"cited_by_count":9}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}
