{"id":"https://openalex.org/W4283778007","doi":"https://doi.org/10.1145/3503161.3547742","title":"Interpretable Melody Generation from Lyrics with Discrete-Valued Adversarial Training","display_name":"Interpretable Melody Generation from Lyrics with Discrete-Valued Adversarial Training","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4283778007","doi":"https://doi.org/10.1145/3503161.3547742"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547742","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547742","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5088285841","display_name":"Wei Duan","orcid":"https://orcid.org/0000-0001-5782-9184"},"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":"Wei Duan","raw_affiliation_strings":["National Institute of Informatics, The Graduate University for Advanced Studies, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, The Graduate University for Advanced Studies, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115076710","display_name":"Zhe Zhang","orcid":"https://orcid.org/0000-0002-7337-0446"},"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":false,"raw_author_name":"Zhe Zhang","raw_affiliation_strings":["National Institute of Informatics, The Graduate University for Advanced Studies, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, The Graduate University for Advanced Studies, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","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":false,"raw_author_name":"Yi Yu","raw_affiliation_strings":["National Institute of Informatics, The Graduate University for Advanced Studies, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, The Graduate University for Advanced Studies, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027561196","display_name":"Keizo Oyama","orcid":"https://orcid.org/0000-0003-4385-8798"},"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":false,"raw_author_name":"Keizo Oyama","raw_affiliation_strings":["National Institute of Informatics, The Graduate University for Advanced Studies, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, The Graduate University for Advanced Studies, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088285841"],"corresponding_institution_ids":["https://openalex.org/I184597095"],"apc_list":null,"apc_paid":null,"fwci":0.7364,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.69636651,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"6973","last_page":"6975"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9918000102043152,"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":0.9894000291824341,"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":0.9640712738037109},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.8827756643295288},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7223522067070007},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.6287979483604431},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5984180569648743},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48047012090682983},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4758424758911133},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.46515947580337524},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39230433106422424},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.11070111393928528}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.9640712738037109},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.8827756643295288},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7223522067070007},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.6287979483604431},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5984180569648743},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48047012090682983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4758424758911133},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.46515947580337524},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39230433106422424},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.11070111393928528},{"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},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3547742","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3547742","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2074308058","https://openalex.org/W2167302452","https://openalex.org/W2413768264","https://openalex.org/W2434741482","https://openalex.org/W2553749962","https://openalex.org/W2772474126","https://openalex.org/W2809621972","https://openalex.org/W2810518847","https://openalex.org/W2919624000","https://openalex.org/W2963226019","https://openalex.org/W3112317145","https://openalex.org/W3154236293","https://openalex.org/W3166855379","https://openalex.org/W3200682172","https://openalex.org/W4287688462","https://openalex.org/W4287802874","https://openalex.org/W6607270920","https://openalex.org/W6636510571","https://openalex.org/W6730185942","https://openalex.org/W6730621950","https://openalex.org/W6776218486","https://openalex.org/W6782590614","https://openalex.org/W6794378322"],"related_works":["https://openalex.org/W2413768264","https://openalex.org/W1984378309","https://openalex.org/W4285428803","https://openalex.org/W2363573956","https://openalex.org/W2953246223","https://openalex.org/W4293320219","https://openalex.org/W4283584549","https://openalex.org/W3110074278","https://openalex.org/W2618858825","https://openalex.org/W2554314924"],"abstract_inverted_index":{"Generating":[0],"melody":[1,30,69],"from":[2,142],"lyrics":[3,27,83],"is":[4,76,88,113],"an":[5],"interesting":[6],"yet":[7],"challenging":[8],"task":[9],"in":[10],"the":[11,19,23,32,56,61,66,80,92,106,111,129],"area":[12],"of":[13,21,35,68,95],"artificial":[14],"intelligence":[15],"and":[16,28,59,84],"music.":[17],"However,":[18],"difficulty":[20],"keeping":[22],"consistency":[24,81],"between":[25,82],"input":[26],"generated":[29,85,130],"limits":[31],"generation":[33,47,57,70,123],"quality":[34],"previous":[36],"works.":[37],"In":[38],"our":[39,43,121],"proposal,":[40],"we":[41],"demonstrate":[42],"proposed":[44],"interpretable":[45],"lyrics-to-melody":[46,122],"system":[48],"which":[49],"can":[50,126],"interact":[51],"with":[52,120],"users":[53,125],"to":[54,78,90,115,128],"understand":[55],"process":[58],"recreate":[60,136],"desired":[62],"songs.":[63],"To":[64],"improve":[65],"reliability":[67],"that":[71],"matches":[72],"lyrics,":[73],"mutual":[74],"information":[75],"exploited":[77,89],"strengthen":[79],"melodies.":[86],"Gumbel-Softmax":[87],"solve":[91],"non-differentiability":[93],"problem":[94],"generating":[96],"discrete":[97],"music":[98,117,144],"attributes":[99],"by":[100,110,140],"Generative":[101],"Adversarial":[102],"Networks":[103],"(GANs).":[104],"Moreover,":[105],"predicted":[107],"probabilities":[108],"output":[109],"generator":[112],"utilized":[114],"recommend":[116],"attributes.":[118,145],"Interacting":[119],"system,":[124],"listen":[127],"AI":[131],"song":[132,139],"as":[133,135],"well":[134],"a":[137],"new":[138],"selecting":[141],"recommended":[143]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}