{"id":"https://openalex.org/W4310987263","doi":"https://doi.org/10.1145/3572031","title":"Melody Generation from Lyrics with Local Interpretability","display_name":"Melody Generation from Lyrics with Local Interpretability","publication_year":2022,"publication_date":"2022-11-29","ids":{"openalex":"https://openalex.org/W4310987263","doi":"https://doi.org/10.1145/3572031"},"language":"en","primary_location":{"id":"doi:10.1145/3572031","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3572031","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/A5101720177","display_name":"Wei Duan","orcid":"https://orcid.org/0000-0002-9007-1667"},"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"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Wei Duan","raw_affiliation_strings":["Digital Content and Media Sciences Research Division, National Institute of Informatics, SOKENDAI, Chiyoda-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Digital Content and Media Sciences Research Division, National Institute of Informatics, SOKENDAI, Chiyoda-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095","https://openalex.org/I200475212"]}]},{"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"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yi Yu","raw_affiliation_strings":["Digital Content and Media Sciences Research Division, National Institute of Informatics, SOKENDAI, Chiyoda-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Digital Content and Media Sciences Research Division, National Institute of Informatics, SOKENDAI, Chiyoda-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095","https://openalex.org/I200475212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028437800","display_name":"Xulong Zhang","orcid":"https://orcid.org/0000-0001-7005-992X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xulong Zhang","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"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":["Department of Computer and Network Engineering, Graduate School of Informatics and Engineering, The University of Electro-Communications, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Network Engineering, Graduate School of Informatics and Engineering, The University of Electro-Communications, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318193","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-4486-8341"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"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"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keizo Oyama","raw_affiliation_strings":["Digital Content and Media Sciences Research Division, National Institute of Informatics, SOKENDAI, Chiyoda-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Digital Content and Media Sciences Research Division, National Institute of Informatics, SOKENDAI, Chiyoda-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095","https://openalex.org/I200475212"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101720177"],"corresponding_institution_ids":["https://openalex.org/I184597095","https://openalex.org/I200475212"],"apc_list":null,"apc_paid":null,"fwci":1.4868,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.82098042,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"19","issue":"3","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9950000047683716,"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":0.9726999998092651,"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/lyrics","display_name":"Lyrics","score":0.9746094942092896},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.8901166915893555},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7828042507171631},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6289241313934326},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4326934814453125},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4027666747570038},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39684951305389404},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.15871375799179077},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.09990721940994263},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.05563974380493164}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.9746094942092896},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.8901166915893555},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7828042507171631},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6289241313934326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4326934814453125},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4027666747570038},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39684951305389404},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.15871375799179077},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.09990721940994263},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.05563974380493164}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3572031","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3572031","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2541443726","https://openalex.org/W2560662714","https://openalex.org/W2565378226","https://openalex.org/W2772474126","https://openalex.org/W2809621972","https://openalex.org/W2968379763","https://openalex.org/W2978223337","https://openalex.org/W2978471471","https://openalex.org/W3087037461","https://openalex.org/W3092850823","https://openalex.org/W3105368110","https://openalex.org/W3112317145","https://openalex.org/W3137125108","https://openalex.org/W3200682172","https://openalex.org/W4287599788","https://openalex.org/W4287802874","https://openalex.org/W4294294142","https://openalex.org/W4295126967","https://openalex.org/W4298289240","https://openalex.org/W4385567278","https://openalex.org/W6776218486","https://openalex.org/W6783411700"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2360952181","https://openalex.org/W4390569940","https://openalex.org/W2888392564","https://openalex.org/W2118466154","https://openalex.org/W4361193272","https://openalex.org/W4310278675","https://openalex.org/W2413768264","https://openalex.org/W1984378309","https://openalex.org/W2363573956"],"abstract_inverted_index":{"Melody":[0],"generation":[1,44,79],"aims":[2],"to":[3,10,49,101,123],"learn":[4],"the":[5,25,38,51,54,103,106,110,116,151],"distribution":[6],"of":[7,27,42,105,112],"real":[8],"melodies":[9,13,59,157],"generate":[11,155],"new":[12],"conditioned":[14,45],"on":[15,46,142],"lyrics,":[16],"which":[17,85,108,131],"has":[18],"been":[19],"a":[20,33,75,143],"very":[21],"interesting":[22],"topic":[23],"in":[24,70,139],"area":[26],"artificial":[28],"intelligence":[29],"and":[30,40,57,96],"music.":[31],"However,":[32],"challenging":[34],"issue":[35],"still":[36],"limits":[37],"quality":[39],"reliability":[41],"melody":[43,78,98],"lyrics:":[47],"how":[48],"enhance":[50],"interpretability":[52],"between":[53,93,136],"input":[55,94],"lyrics":[56,81,95,129,159],"generated":[58,97],"so":[60],"humans":[61],"can":[62,154],"understand":[63],"their":[64],"relationships.":[65],"To":[66],"solve":[67],"this":[68,71],"issue,":[69],"article,":[72],"we":[73],"propose":[74],"model":[76],"for":[77],"from":[80,128,158],"with":[82,146,161],"local":[83],"interpretability,":[84],"contains":[86],"two":[87],"significant":[88],"contributions:":[89],"(i)":[90],"Mutual":[91],"information":[92],"is":[99,121],"exploited":[100],"instruct":[102],"training":[104,117],"network,":[107],"avoids":[109],"loss":[111],"content":[113],"consistency":[114],"during":[115],"stage.":[118],"(ii)":[119],"Transformer":[120],"explored":[122],"efficiently":[124],"extract":[125],"semantic":[126],"features":[127],"sequences,":[130],"provides":[132],"more":[133],"interpretable":[134],"correlations":[135],"different":[137],"syllables":[138],"lyrics.":[140],"Experiments":[141],"large-scale":[144],"dataset":[145],"paired":[147],"lyrics-melodies":[148],"demonstrate":[149],"that":[150],"proposed":[152],"approach":[153],"higher-quality":[156],"compared":[160],"existing":[162],"methods.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
