{"id":"https://openalex.org/W3015516707","doi":"https://doi.org/10.1109/icassp40776.2020.9053950","title":"Korean Singing Voice Synthesis Based on Auto-Regressive Boundary Equilibrium Gan","display_name":"Korean Singing Voice Synthesis Based on Auto-Regressive Boundary Equilibrium Gan","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015516707","doi":"https://doi.org/10.1109/icassp40776.2020.9053950","mag":"3015516707"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053950","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":["Graduate School of Culture Technology, KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of Culture Technology, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042687506","display_name":"Won\u2010Il Kim","orcid":"https://orcid.org/0000-0002-0465-0794"},"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":"Wonil Kim","raw_affiliation_strings":["Graduate School of Culture Technology, KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of Culture Technology, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042566195","display_name":"Saebyul Park","orcid":"https://orcid.org/0000-0001-6002-9217"},"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":"Saebyul Park","raw_affiliation_strings":["Graduate School of Culture Technology, KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of Culture Technology, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014282591","display_name":"Sangeon Yong","orcid":null},"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":"Sangeon Yong","raw_affiliation_strings":["Graduate School of Culture Technology, KAIST, Daejeon, South Korea"],"affiliations":[{"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":["Graduate School of Culture Technology, KAIST, Daejeon, South Korea"],"affiliations":[{"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":5,"corresponding_author_ids":["https://openalex.org/A5102743910"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":3.7884,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.94088216,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7234","last_page":"7238"},"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/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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9959999918937683,"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/spectrogram","display_name":"Spectrogram","score":0.8113085627555847},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.768020510673523},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7430258393287659},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7162540555000305},{"id":"https://openalex.org/keywords/vibrato","display_name":"Vibrato","score":0.5968857407569885},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4646086096763611},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4549441337585449},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.42592841386795044},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4187832772731781},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.32457274198532104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29281821846961975},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18305715918540955}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8113085627555847},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.768020510673523},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7430258393287659},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7162540555000305},{"id":"https://openalex.org/C2781100714","wikidata":"https://www.wikidata.org/wiki/Q377435","display_name":"Vibrato","level":3,"score":0.5968857407569885},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4646086096763611},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4549441337585449},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.42592841386795044},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4187832772731781},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.32457274198532104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29281821846961975},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18305715918540955},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053950","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1512786422","https://openalex.org/W1522301498","https://openalex.org/W1901129140","https://openalex.org/W2099471712","https://openalex.org/W2120847449","https://openalex.org/W2124097505","https://openalex.org/W2173520492","https://openalex.org/W2515336442","https://openalex.org/W2519091744","https://openalex.org/W2584505851","https://openalex.org/W2605195953","https://openalex.org/W2619368999","https://openalex.org/W2774707525","https://openalex.org/W2778460379","https://openalex.org/W2889244839","https://openalex.org/W2910577860","https://openalex.org/W2940405045","https://openalex.org/W2949382160","https://openalex.org/W2962883485","https://openalex.org/W2963073614","https://openalex.org/W2963609956","https://openalex.org/W2963684088","https://openalex.org/W2964121744","https://openalex.org/W2964229681","https://openalex.org/W2964243274","https://openalex.org/W2973046048","https://openalex.org/W2984106626","https://openalex.org/W4295274059","https://openalex.org/W4320013936","https://openalex.org/W6630833833","https://openalex.org/W6631190155","https://openalex.org/W6639824700","https://openalex.org/W6678318511","https://openalex.org/W6685352114","https://openalex.org/W6736155344","https://openalex.org/W6746914816","https://openalex.org/W6758675244","https://openalex.org/W6765987481"],"related_works":["https://openalex.org/W2373880408","https://openalex.org/W405661683","https://openalex.org/W2532856746","https://openalex.org/W238390473","https://openalex.org/W2119168266","https://openalex.org/W2978145617","https://openalex.org/W2108382268","https://openalex.org/W4230480656","https://openalex.org/W2097873655","https://openalex.org/W2023774214"],"abstract_inverted_index":{"Singing":[0],"voice":[1,108],"synthesis":[2,109],"is":[3,66],"a":[4,14,105],"generative":[5,45],"task":[6],"that":[7,111,119,150],"involves":[8],"not":[9],"only":[10],"multidimensional":[11],"controls":[12],"of":[13,78],"singer":[15],"model":[16],"such":[17,33,158],"as":[18,34,53,159],"phonetic":[19],"modulation":[20],"by":[21,26],"lyrics":[22],"and":[23,37,90,144,163],"pitch":[24,161],"control":[25],"music":[27],"score":[28],"but":[29,59],"also":[30,148],"expressive":[31],"elements":[32],"breath":[35,164],"sounds":[36],"vibrato.":[38],"Recently,":[39],"end-to-end":[40],"learning":[41],"models":[42],"based":[43],"on":[44],"adversarial":[46],"network":[47],"(GAN)":[48],"have":[49],"drawn":[50],"much":[51],"interest":[52],"it":[54,72],"requires":[55],"less":[56],"domain-specific":[57],"processing":[58],"provides":[60],"high":[61],"sound":[62],"quality.":[63],"When":[64],"GAN":[65,126,142],"applied":[67],"to":[68,81,139],"the":[69,76,97,113,123,129,134,140],"audio":[70,79,98],"domain,":[71],"entails":[73],"several":[74],"issues:":[75],"choice":[77],"representation":[80],"generate,":[82],"handling":[83],"temporal":[84],"continuity":[85],"between":[86],"two":[87],"adjacent":[88],"outputs,":[89],"finding":[91],"an":[92,116],"effective":[93],"loss":[94],"metric":[95],"for":[96],"representation.":[99],"In":[100],"this":[101],"paper,":[102],"we":[103,132],"propose":[104],"Korean":[106],"singing":[107],"system":[110],"addresses":[112],"issues":[114],"using":[115],"auto-regressive":[117],"algorithm":[118],"generates":[120],"spectrogram":[121],"with":[122],"boundary":[124],"equilibrium":[125],"objective.":[127],"Through":[128],"qualitative":[130],"test,":[131],"show":[133,149],"proposed":[135,152],"methods":[136],"are":[137],"superior":[138],"original":[141],"objective":[143],"non-auto-regressive":[145],"model.":[146],"We":[147],"our":[151],"method":[153],"can":[154],"render":[155],"natural":[156],"expressions":[157],"continuous":[160],"contours":[162],"sounds.":[165]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
