{"id":"https://openalex.org/W7134189546","doi":"https://doi.org/10.1109/bigdata66926.2025.11401776","title":"Chord Latent Decoupling for Music Mashups","display_name":"Chord Latent Decoupling for Music Mashups","publication_year":2025,"publication_date":"2025-12-08","ids":{"openalex":"https://openalex.org/W7134189546","doi":"https://doi.org/10.1109/bigdata66926.2025.11401776"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata66926.2025.11401776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata66926.2025.11401776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","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":"https://openalex.org/A5128182569","display_name":"Yu Foon Darin CHAU","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yu Foon Darin Chau","raw_affiliation_strings":["Hong Kong University of Science and Technology,Department of Computer Science and Engineering,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Department of Computer Science and Engineering,Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056541447","display_name":"Andrew Horner","orcid":"https://orcid.org/0000-0002-9795-5190"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Andrew Horner","raw_affiliation_strings":["Hong Kong University of Science and Technology,Department of Computer Science and Engineering,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Department of Computer Science and Engineering,Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.66771081,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4973","last_page":"4980"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.6614999771118164,"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":0.6614999771118164,"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":0.25619998574256897,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.005799999926239252,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.7429999709129333},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.524399995803833},{"id":"https://openalex.org/keywords/mashup","display_name":"Mashup","score":0.5115000009536743},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.4050999879837036},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.39100000262260437},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.3813999891281128},{"id":"https://openalex.org/keywords/tonality","display_name":"Tonality","score":0.3734999895095825},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.37070000171661377},{"id":"https://openalex.org/keywords/unison","display_name":"Unison","score":0.3626999855041504}],"concepts":[{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.7429999709129333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6923999786376953},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.524399995803833},{"id":"https://openalex.org/C196126337","wikidata":"https://www.wikidata.org/wiki/Q821080","display_name":"Mashup","level":4,"score":0.5115000009536743},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49540001153945923},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.39100000262260437},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C2776275044","wikidata":"https://www.wikidata.org/wiki/Q192822","display_name":"Tonality","level":3,"score":0.3734999895095825},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.37070000171661377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36480000615119934},{"id":"https://openalex.org/C2780304638","wikidata":"https://www.wikidata.org/wiki/Q176224","display_name":"Unison","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.3617999851703644},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.35589998960494995},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.3398999869823456},{"id":"https://openalex.org/C2776453491","wikidata":"https://www.wikidata.org/wiki/Q5659234","display_name":"Harmony (color)","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3174999952316284},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.29159998893737793},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28679999709129333},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2718000113964081},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.27000001072883606},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.26840001344680786},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26109999418258667},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.25850000977516174},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2524999976158142}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata66926.2025.11401776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata66926.2025.11401776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-169210","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-169210","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1978421240","https://openalex.org/W1982446897","https://openalex.org/W2036405930","https://openalex.org/W2552400013","https://openalex.org/W2883116200","https://openalex.org/W2962896155","https://openalex.org/W2963408210","https://openalex.org/W2964051853","https://openalex.org/W2964287748","https://openalex.org/W2972411915","https://openalex.org/W3015440759","https://openalex.org/W3037149862","https://openalex.org/W3080857286","https://openalex.org/W3145867403","https://openalex.org/W3195817861","https://openalex.org/W3207894480","https://openalex.org/W4385822304","https://openalex.org/W4390874529","https://openalex.org/W4413145954"],"related_works":[],"abstract_inverted_index":{"Musical":[0],"mashups":[1],"increasingly":[2],"serve":[3],"as":[4,39,181],"a":[5,29,40,70,78,182],"testbed":[6],"for":[7,32,166,173],"computational":[8],"creativity,":[9],"yet":[10],"existing":[11],"automated":[12],"systems":[13],"often":[14],"reduce":[15],"harmonic":[16,106,137],"compatibility":[17],"to":[18,65,185],"surface-level":[19],"matches":[20],"in":[21,125,147,188],"key":[22],"or":[23],"chord":[24,33,57],"labels.":[25],"This":[26],"paper":[27],"proposes":[28],"two-phase":[30],"framework":[31],"latent":[34,44,72,81],"decoupling":[35,180],"that":[36,123,136],"treats":[37],"harmony":[38,71,128,164],"transferable":[41],"and":[42,62,76,88,135,152,155,168,170],"disentangled":[43,98],"dimension,":[45],"enabling":[46],"controllable":[47],"mashup":[48,133],"generation":[49],"beyond":[50],"traditional":[51],"signal-level":[52],"heuristics.":[53],"Our":[54,176],"method":[55],"extracts":[56],"latents":[58],"with":[59,118,131],"timbre-invariant":[60],"training,":[61],"adversarial":[63],"objectives":[64],"factorize":[66],"music":[67,115,190],"into":[68],"(i)":[69],"capturing":[73],"chordal":[74],"progression,":[75],"(ii)":[77],"complementary":[79],"non-harmony":[80],"encoding":[82],"other":[83],"information":[84],"like":[85],"melody,":[86],"rhythm,":[87],"timbre.":[89],"A":[90],"joint":[91],"decoder":[92,153],"reconstructs":[93],"coherent":[94],"audio":[95],"from":[96],"these":[97],"components,":[99],"permitting":[100],"crosssong":[101],"recomposition":[102],"where":[103],"one":[104],"track's":[105],"structure":[107],"guides":[108],"another's":[109],"musical":[110],"content.":[111],"Experiments":[112],"on":[113],"large-scale":[114],"datasets,":[116],"combined":[117],"perceptual":[119],"listening":[120],"studies,":[121],"demonstrate":[122],"proximity":[124],"the":[126],"learned":[127],"space":[129],"correlates":[130],"perceived":[132],"compatibility,":[134],"transfer":[138],"produces":[139],"coherent,":[140],"musically":[141],"interpretable":[142,186],"results.":[143],"We":[144],"discuss":[145],"limitations":[146],"supervision":[148],"granularity,":[149],"residual":[150],"leakage,":[151],"fidelity,":[154],"outline":[156],"some":[157],"salient":[158],"directions:":[159],"scalable":[160],"pseudo-label":[161],"distillation,":[162],"cross-modal":[163],"embeddings":[165],"retrieval":[167],"recommendation,":[169],"structure-aware":[171],"alignment":[172],"long-horizon":[174],"generation.":[175,191],"results":[177],"highlight":[178],"chord-latent":[179],"data-driven":[183],"path":[184],"control":[187],"AI":[189]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-09T00:00:00"}