{"id":"https://openalex.org/W2963435138","doi":"https://doi.org/10.1145/3281746","title":"Deep Cross-Modal Correlation Learning for Audio and Lyrics in Music Retrieval","display_name":"Deep Cross-Modal Correlation Learning for Audio and Lyrics in Music Retrieval","publication_year":2019,"publication_date":"2019-02-13","ids":{"openalex":"https://openalex.org/W2963435138","doi":"https://doi.org/10.1145/3281746","mag":"2963435138"},"language":"en","primary_location":{"id":"doi:10.1145/3281746","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3281746","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-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/A5100745222","display_name":"Yi Yu","orcid":"https://orcid.org/0000-0002-0294-6620"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yi Yu","raw_affiliation_strings":["National Institute of Informatics, Chiyoda-ku, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-0294-6620","affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Chiyoda-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033599028","display_name":"Suhua Tang","orcid":"https://orcid.org/0000-0002-5784-8411"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Suhua Tang","raw_affiliation_strings":["The University of Electro-Communications, Chofu, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications, Chofu, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102766824","display_name":"Francisco Raposo","orcid":"https://orcid.org/0000-0003-1044-5989"},"institutions":[{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]},{"id":"https://openalex.org/I4210105462","display_name":"Lus\u00edada University of Lisbon","ror":"https://ror.org/00zjprf31","country_code":"PT","type":"education","lineage":["https://openalex.org/I4210105462","https://openalex.org/I4401200244"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Francisco Raposo","raw_affiliation_strings":["Universidade de Lisboa, Lisboa, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade de Lisboa, Lisboa, Portugal","institution_ids":["https://openalex.org/I4210105462","https://openalex.org/I141596103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100333516","display_name":"Lei Chen","orcid":"https://orcid.org/0000-0002-8257-5806"},"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":"Lei Chen","raw_affiliation_strings":["Hong Kong University of Science and Technology, Kowloon, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100745222"],"corresponding_institution_ids":["https://openalex.org/I184597095"],"apc_list":null,"apc_paid":null,"fwci":13.854,"has_fulltext":false,"cited_by_count":106,"citation_normalized_percentile":{"value":0.99366819,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"15","issue":"1","first_page":"1","last_page":"16"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9962000250816345,"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":0.9742000102996826,"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/lyrics","display_name":"Lyrics","score":0.8462578058242798},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7412198781967163},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5995975732803345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5736590623855591},{"id":"https://openalex.org/keywords/canonical-correlation","display_name":"Canonical correlation","score":0.517458975315094},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5149303078651428},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5104140639305115},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5045846700668335},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4947151839733124},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.490432471036911},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4556576907634735},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.43942901492118835},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43663328886032104},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4198855757713318},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3344835042953491},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14869993925094604},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08923700451850891}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.8462578058242798},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7412198781967163},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5995975732803345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5736590623855591},{"id":"https://openalex.org/C153874254","wikidata":"https://www.wikidata.org/wiki/Q115542","display_name":"Canonical correlation","level":2,"score":0.517458975315094},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5149303078651428},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5104140639305115},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5045846700668335},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4947151839733124},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.490432471036911},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4556576907634735},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.43942901492118835},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43663328886032104},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4198855757713318},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3344835042953491},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14869993925094604},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08923700451850891},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3281746","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3281746","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-96079","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-96079","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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W306648316","https://openalex.org/W395933519","https://openalex.org/W1825426646","https://openalex.org/W1949478088","https://openalex.org/W1980771692","https://openalex.org/W2025341678","https://openalex.org/W2064675550","https://openalex.org/W2071103260","https://openalex.org/W2106277773","https://openalex.org/W2113409081","https://openalex.org/W2113613324","https://openalex.org/W2116777898","https://openalex.org/W2116867711","https://openalex.org/W2123442489","https://openalex.org/W2167537125","https://openalex.org/W2266728343","https://openalex.org/W2340600463","https://openalex.org/W2509286793","https://openalex.org/W2526050071","https://openalex.org/W2552579943","https://openalex.org/W2563031223","https://openalex.org/W2618530766","https://openalex.org/W2742121874","https://openalex.org/W2782280045","https://openalex.org/W2963633722"],"related_works":["https://openalex.org/W2360952181","https://openalex.org/W4310670065","https://openalex.org/W3214861561","https://openalex.org/W2389838651","https://openalex.org/W2597614303","https://openalex.org/W437317580","https://openalex.org/W2352995288","https://openalex.org/W2365365224","https://openalex.org/W3046630152","https://openalex.org/W4283320496"],"abstract_inverted_index":{"Deep":[0],"cross-modal":[1,9,28,79,175,264],"learning":[2,16,30,81,134,186,261],"has":[3],"successfully":[4],"demonstrated":[5],"excellent":[6],"performance":[7],"in":[8,57,96,161,263],"multimedia":[10],"retrieval,":[11],"with":[12],"the":[13,50,64,102,119,126,135,162,234,254,257],"aim":[14],"of":[15,34,52,55,121,215,237,256],"joint":[17,191],"representations":[18],"between":[19,68,138,177],"different":[20,35,97],"data":[21,36],"modalities.":[22],"Unfortunately,":[23],"little":[24],"research":[25],"focuses":[26],"on":[27],"correlation":[29,67,80,109,137,176,185,260],"where":[31,106,181],"temporal":[32,53,122,136,197,235],"structures":[33,54,236],"modalities,":[37],"such":[38],"as":[39,113,165,201],"audio":[40,69,89,139,163,178,209,243],"and":[41,70,91,140,179,184,190,220],"lyrics,":[42,180],"should":[43],"be":[44],"taken":[45],"into":[46],"account.":[47],"Stemming":[48],"from":[49],"characteristic":[51],"music":[56,238,265],"nature,":[58],"we":[59,75,205],"are":[60,99,159,187],"motivated":[61],"to":[62,101,117,153,173,226,244,250],"learn":[63,174],"deep":[65,78,85,131,259],"sequential":[66],"lyrics.":[71,141,155],"In":[72],"this":[73],"work,":[74],"propose":[76,169],"a":[77,212,222,228],"architecture":[82],"involving":[83],"two-branch":[84],"neural":[86,224],"networks":[87],"for":[88,133,202],"modality":[90,93],"text":[92],"(lyrics).":[94],"Data":[95],"modalities":[98],"converted":[100],"same":[103],"canonical":[104,108],"space":[105],"intermodal":[107],"analysis":[110],"is":[111,125,151,193],"utilized":[112],"an":[114,170,208],"objective":[115],"function":[116],"calculate":[118],"similarity":[120],"structures.":[123,198],"This":[124],"first":[127],"study":[128],"that":[129,231],"uses":[130],"architectures":[132,262],"A":[142],"pretrained":[143],"Doc2Vec":[144],"model":[145],"followed":[146],"by":[147,195,211],"fully":[148],"connected":[149],"layers":[150],"used":[152],"represent":[154,207],"Two":[156],"significant":[157],"contributions":[158],"made":[160],"branch,":[164],"follows:":[166],"(i)":[167],"We":[168],"end-to-end":[171],"network":[172,225],"feature":[182,203,230],"extraction":[183],"simultaneously":[188],"performed":[189],"representation":[192],"learned":[194],"considering":[196],"(ii)":[199],"And,":[200],"extraction,":[204],"further":[206],"signal":[210],"short":[213],"sequence":[214],"local":[216],"summaries":[217],"(VGG16":[218],"features)":[219],"apply":[221],"recurrent":[223],"compute":[227],"compact":[229],"better":[232],"learns":[233],"audio.":[239],"Experimental":[240],"results,":[241],"using":[242,248],"retrieve":[245,251],"lyrics":[246,249],"or":[247],"audio,":[252],"verify":[253],"effectiveness":[255],"proposed":[258],"retrieval.":[266]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}