{"id":"https://openalex.org/W3204116061","doi":"https://doi.org/10.1109/aivr52153.2021.00067","title":"A Survey on Recent Deep Learning-driven Singing Voice Synthesis Systems","display_name":"A Survey on Recent Deep Learning-driven Singing Voice Synthesis Systems","publication_year":2021,"publication_date":"2021-11-01","ids":{"openalex":"https://openalex.org/W3204116061","doi":"https://doi.org/10.1109/aivr52153.2021.00067","mag":"3204116061"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/aivr52153.2021.00067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/pdf/2110.02511","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025897761","display_name":"Yin-Ping Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yin-Ping Cho","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036605364","display_name":"Fu-Rong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Fu-Rong Yang","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047834625","display_name":"Yung\u2013Chuan Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yung-Chuan Chang","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019455184","display_name":"Ching-Ting Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ching-Ting Cheng","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354384","display_name":"Xiaohan Wang","orcid":"https://orcid.org/0000-0002-5714-2013"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Xiao-Han Wang","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100770932","display_name":"Yiwen Liu","orcid":"https://orcid.org/0000-0001-6677-7961"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Wen Liu","raw_affiliation_strings":["National Tsing Hua University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Tsing Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.911753,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":83,"max":84},"biblio":{"volume":null,"issue":null,"first_page":"319","last_page":"323"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998,"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":0.9998,"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":0.9997,"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":0.9994,"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/lyrics","display_name":"Lyrics","score":0.79546285}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.87889636},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.84777033},{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.79546285},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6876875},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6564877},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.51841235},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.47626945},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4721016},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.46817034},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44443643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3928656},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.091248244},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08625364},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/aivr52153.2021.00067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.02511","pdf_url":"http://arxiv.org/pdf/2110.02511","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.02511","pdf_url":"http://arxiv.org/pdf/2110.02511","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"score":0.79,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":39,"referenced_works":["https://openalex.org/W2102870814","https://openalex.org/W2107860279","https://openalex.org/W2124097505","https://openalex.org/W2154920538","https://openalex.org/W2471520273","https://openalex.org/W2515336442","https://openalex.org/W2519091744","https://openalex.org/W2739748921","https://openalex.org/W2778460379","https://openalex.org/W2794490148","https://openalex.org/W2889244839","https://openalex.org/W2903032817","https://openalex.org/W2937242376","https://openalex.org/W2940405045","https://openalex.org/W2946200149","https://openalex.org/W2949382160","https://openalex.org/W2963403868","https://openalex.org/W2970730223","https://openalex.org/W2973046048","https://openalex.org/W29794711","https://openalex.org/W2982079758","https://openalex.org/W3015338123","https://openalex.org/W3015437531","https://openalex.org/W3033411150","https://openalex.org/W3035430139","https://openalex.org/W3036167779","https://openalex.org/W3082910224","https://openalex.org/W3097514409","https://openalex.org/W3100572490","https://openalex.org/W3112624375","https://openalex.org/W3130016944","https://openalex.org/W3133525064","https://openalex.org/W3148333649","https://openalex.org/W3158762648","https://openalex.org/W3163031268","https://openalex.org/W3169635929","https://openalex.org/W3190244907","https://openalex.org/W3198020407","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W2946856121","https://openalex.org/W2433276473","https://openalex.org/W2378183644","https://openalex.org/W2287414930","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W1984347656","https://openalex.org/W1914543332","https://openalex.org/W1537411440"],"abstract_inverted_index":{"Singing":[0],"voice":[1],"synthesis":[2],"(SVS)":[3],"is":[4],"a":[5,52],"task":[6],"that":[7,32],"aims":[8,66],"to":[9,14,67,79,112],"generate":[10],"audio":[11],"signals":[12],"according":[13],"musical":[15],"scores":[16],"and":[17,25,58,85,89,107,119],"lyrics.":[18],"With":[19],"its":[20],"multifaceted":[21],"nature":[22],"concerning":[23],"music":[24],"language,":[26],"producing":[27],"singing":[28,62],"voices":[29],"indistinguishable":[30],"from":[31],"of":[33,45,60,70,93,104],"human":[34],"singers":[35],"has":[36],"always":[37],"remained":[38],"an":[39],"unfulfilled":[40],"pursuit.":[41],"Nonetheless,":[42],"the":[43,56,71,87,94,100,109],"advancements":[44],"deep":[46,73],"learning":[47],"techniques":[48],"have":[49],"brought":[50],"about":[51],"substantial":[53],"leap":[54],"in":[55,116],"quality":[57],"naturalness":[59],"synthesized":[61],"voice.":[63],"This":[64],"paper":[65],"review":[68],"some":[69],"state-of-the-art":[72],"learning-driven":[74],"SVS":[75],"systems.":[76,96],"We":[77],"intend":[78],"summarize":[80],"their":[81],"deployed":[82],"model":[83],"architectures":[84],"identify":[86],"strengths":[88],"limitations":[90],"for":[91],"each":[92],"introduced":[95],"Thereby,":[97],"we":[98],"picture":[99],"recent":[101],"advancement":[102],"trajectory":[103],"this":[105],"field":[106],"conclude":[108],"challenges":[110],"left":[111],"be":[113],"resolved":[114],"both":[115],"commercial":[117],"applications":[118],"academic":[120],"research.":[121]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3204116061","counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2024-12-13T03:38:57.965792","created_date":"2021-10-11"}