{"id":"https://openalex.org/W4415541268","doi":"https://doi.org/10.1145/3746027.3754812","title":"Temporal-Conditioned Symbolic Alignment for Controllable Text-to-Music Generation","display_name":"Temporal-Conditioned Symbolic Alignment for Controllable Text-to-Music Generation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415541268","doi":"https://doi.org/10.1145/3746027.3754812"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754812","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zihao Zhang","orcid":"https://orcid.org/0009-0008-0668-4462"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Zhang","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-0668-4462","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043728985","display_name":"Xingjiao Wu","orcid":"https://orcid.org/0000-0001-9146-051X"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingjiao Wu","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9146-051X","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102558323","display_name":"Junjie Xu","orcid":"https://orcid.org/0009-0007-1965-867X"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Xu","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-1965-867X","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103028836","display_name":"Tianlong Ma","orcid":"https://orcid.org/0000-0003-4079-7897"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianlong Ma","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4079-7897","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052913873","display_name":"Tangren Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tangren Yao","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-5039-8189","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084590062","display_name":"Wen Wu","orcid":"https://orcid.org/0000-0002-2132-5993"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Wu","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2132-5993","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010540039","display_name":"Liang He","orcid":"https://orcid.org/0000-0002-4723-5486"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4723-5486","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10728","last_page":"10737"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9980999827384949,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/chord","display_name":"Chord (peer-to-peer)","score":0.6513000130653381},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5231000185012817},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.40470001101493835},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.38029998540878296},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.3765000104904175},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.34310001134872437},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.33730000257492065},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.33640000224113464},{"id":"https://openalex.org/keywords/musical-notation","display_name":"Musical notation","score":0.33629998564720154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7055000066757202},{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.6513000130653381},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5231000185012817},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.415800005197525},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.40470001101493835},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37770000100135803},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3765000104904175},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33640000224113464},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.33629998564720154},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.3084999918937683},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C50637493","wikidata":"https://www.wikidata.org/wiki/Q1136781","display_name":"Morphing","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C143857728","wikidata":"https://www.wikidata.org/wiki/Q193544","display_name":"Music theory","level":3,"score":0.2653999924659729},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754812","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2093341630","https://openalex.org/W2593116425","https://openalex.org/W2766606815","https://openalex.org/W2948556824","https://openalex.org/W3104570641","https://openalex.org/W4312933868","https://openalex.org/W4377719641","https://openalex.org/W4389519221","https://openalex.org/W4390872297","https://openalex.org/W4398226295","https://openalex.org/W4402671601","https://openalex.org/W4403780757"],"related_works":[],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"Text-to-Music":[3,64],"(T2M)":[4],"generation":[5,113,174],"models":[6,20],"have":[7,21],"rapidly":[8],"emerged":[9],"as":[10,112],"powerful":[11],"tools":[12],"in":[13,25,38,44,76],"content":[14,193],"creation":[15],"across":[16],"fields.":[17],"While":[18],"existing":[19],"made":[22],"notable":[23],"progress":[24],"sound":[26],"quality,":[27],"instrument":[28],"identification,":[29],"and":[30,42,49,107,139,160,191],"stylistic":[31],"alignment,":[32],"they":[33],"still":[34],"exhibit":[35],"clear":[36],"limitations":[37],"modeling":[39],"musical":[40,182],"structure":[41],"musicality-particularly":[43],"terms":[45],"of":[46,163],"harmonic":[47,158],"coherence":[48,162],"rhythmic":[50,108],"alignment.":[51],"To":[52,115],"address":[53],"these":[54,117],"issues,":[55],"we":[56,80,121,130,145],"propose":[57,131],"a":[58,82,123,132,147],"Temporal-Conditioned":[59],"Symbolic":[60],"Alignment":[61],"for":[62,187],"Controllable":[63],"Generation(TCSA),":[65],"which":[66,103],"introduces":[67],"explicit":[68],"local":[69,118],"condition":[70],"controls":[71],"to":[72,136,155],"enhance":[73],"structural":[74,142,161],"fidelity":[75],"music":[77,83,99,189],"generation.":[78],"Specifically,":[79],"design":[81],"theory":[84,100],"enrichment":[85],"strategy":[86,135],"based":[87,151],"on":[88,152],"GPT-2":[89],"that":[90,170],"transforms":[91],"input":[92],"text":[93],"into":[94],"detailed":[95],"descriptions":[96],"with":[97],"embedded":[98],"knowledge,":[101],"from":[102],"accurate":[104],"chord":[105],"progressions":[106],"patterns":[109],"are":[110],"extracted":[111],"conditions.":[114],"synchronize":[116],"features":[119],"effectively,":[120],"develop":[122],"temporal":[124],"alignment":[125],"feature":[126],"fusion":[127],"mechanism.":[128],"Additionally,":[129],"layer-skipping":[133],"fine-tuning":[134],"avoid":[137],"overfitting":[138],"enable":[140],"fine-grained":[141],"modeling.":[143],"Finally,":[144],"introduce":[146],"perception-driven":[148],"loss":[149],"function":[150],"Mel":[153],"spectrograms":[154],"optimize":[156],"the":[157,164],"consistency":[159],"generated":[165],"music.":[166],"Experimental":[167],"results":[168],"demonstrate":[169],"TCSA":[171],"achieves":[172],"competitive":[173],"quality":[175],"while":[176],"offering":[177],"significantly":[178],"improved":[179],"controllability":[180],"over":[181],"structure,":[183],"making":[184],"it":[185],"well-suited":[186],"professional":[188],"production":[190],"refined":[192],"creation.":[194]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}