{"id":"https://openalex.org/W3207038517","doi":"https://doi.org/10.1109/icassp43922.2022.9747422","title":"A Melody-Unsupervision Model for Singing Voice Synthesis","display_name":"A Melody-Unsupervision Model for Singing Voice Synthesis","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3207038517","doi":"https://doi.org/10.1109/icassp43922.2022.9747422","mag":"3207038517"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747422","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102743910","display_name":"Soonbeom Choi","orcid":"https://orcid.org/0000-0002-4446-6174"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Soonbeom Choi","raw_affiliation_strings":["KAIST,Graduate School of Culture Technology,Daejeon,South Korea","Graduate School of Culture Technology, KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,Graduate School of Culture Technology,Daejeon,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Graduate School of Culture Technology, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056437111","display_name":"Juhan Nam","orcid":"https://orcid.org/0000-0003-2664-2119"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juhan Nam","raw_affiliation_strings":["KAIST,Graduate School of Culture Technology,Daejeon,South Korea","Graduate School of Culture Technology, KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,Graduate School of Culture Technology,Daejeon,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Graduate School of Culture Technology, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102743910"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":0.835,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.72814968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"33","issue":null,"first_page":"7242","last_page":"7246"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.9414184093475342},{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.8458847403526306},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8132812976837158},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7869254946708679},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5386239290237427},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5020782947540283},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4522157907485962},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.4447745978832245},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42871496081352234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3507792353630066},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.14241907000541687},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09638261795043945}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9414184093475342},{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.8458847403526306},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8132812976837158},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7869254946708679},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5386239290237427},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5020782947540283},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4522157907485962},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.4447745978832245},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42871496081352234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3507792353630066},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.14241907000541687},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09638261795043945},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747422","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2519091744","https://openalex.org/W2747070883","https://openalex.org/W2767052532","https://openalex.org/W2778460379","https://openalex.org/W2889244839","https://openalex.org/W2892009249","https://openalex.org/W2911291251","https://openalex.org/W2937242376","https://openalex.org/W2949382160","https://openalex.org/W2963300588","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2964243274","https://openalex.org/W2972389417","https://openalex.org/W2973046048","https://openalex.org/W3015338123","https://openalex.org/W3015457435","https://openalex.org/W3015499232","https://openalex.org/W3015516707","https://openalex.org/W3016250102","https://openalex.org/W3025165719","https://openalex.org/W3081279708","https://openalex.org/W3092028330","https://openalex.org/W3097152652","https://openalex.org/W3097514409","https://openalex.org/W3097777922","https://openalex.org/W3098403858","https://openalex.org/W3196760057","https://openalex.org/W6631190155","https://openalex.org/W6749489859","https://openalex.org/W6761725420","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W2360952181","https://openalex.org/W2118466154","https://openalex.org/W2597614303","https://openalex.org/W634160686","https://openalex.org/W4310670065","https://openalex.org/W1984378309","https://openalex.org/W2413768264","https://openalex.org/W2378183644","https://openalex.org/W2363573956","https://openalex.org/W2287414930"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"in":[2,12,25,54,77,91,110,132,169],"singing":[3,27,82,105,144,167],"voice":[4,28,83,106,168],"synthesis":[5,29],"have":[6],"achieved":[7],"high-quality":[8],"results":[9],"leveraging":[10],"advances":[11],"text-to-speech":[13],"models":[14,30],"based":[15],"on":[16],"deep":[17],"neural":[18],"networks.":[19],"One":[20],"of":[21,99,123,142,155],"the":[22,57,62,121,139,150],"main":[23],"issues":[24],"training":[26,58,78],"is":[31,49,97,153],"that":[32,69,149],"they":[33],"require":[34],"melody":[35,87,128],"and":[36,88,103,134,161],"lyric":[37],"labels":[38,163],"to":[39],"be":[40,117],"temporally":[41,126],"aligned":[42,127],"with":[43,125,158],"audio":[44,84,140,160],"data.":[45,59],"The":[46,94,114],"temporal":[47,75],"alignment":[48,76],"a":[50,66,86,100,104],"time-exhausting":[51],"manual":[52],"work":[53],"preparing":[55],"for":[56],"To":[60],"address":[61],"issue,":[63],"we":[64,137],"propose":[65],"melody-unsupervision":[67,133],"model":[68,96,115,152],"requires":[70],"only":[71],"audio-and-lyrics":[72],"pairs":[73],"without":[74],"time":[79],"but":[80,164],"generates":[81],"given":[85],"lyrics":[89],"input":[90],"inference":[92,170],"time.":[93,171],"proposed":[95,151],"composed":[98],"phoneme":[101],"classifier":[102],"generator":[107],"jointly":[108],"trained":[109,157],"an":[111],"end-to-end":[112],"manner.":[113],"can":[116,165],"fine-tuned":[118],"by":[119],"adjusting":[120],"amount":[122],"supervision":[124],"labels.":[129],"Through":[130],"experiments":[131],"semi-supervision":[135],"settings,":[136],"compare":[138],"quality":[141],"synthesized":[143],"voice.":[145],"We":[146],"also":[147],"show":[148],"capable":[154],"being":[156],"speech":[159],"text":[162],"generate":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}