{"id":"https://openalex.org/W4399527496","doi":"https://doi.org/10.1109/tce.2024.3412053","title":"FGP-GAN: Fine-Grained Perception Integrated Generative Adversarial Network for Expressive Mandarin Singing Voice Synthesis","display_name":"FGP-GAN: Fine-Grained Perception Integrated Generative Adversarial Network for Expressive Mandarin Singing Voice Synthesis","publication_year":2024,"publication_date":"2024-06-11","ids":{"openalex":"https://openalex.org/W4399527496","doi":"https://doi.org/10.1109/tce.2024.3412053"},"language":"en","primary_location":{"id":"doi:10.1109/tce.2024.3412053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tce.2024.3412053","pdf_url":null,"source":{"id":"https://openalex.org/S126824455","display_name":"IEEE Transactions on Consumer Electronics","issn_l":"0098-3063","issn":["0098-3063","1558-4127"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Consumer Electronics","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/A5101915303","display_name":"Xin Liu","orcid":"https://orcid.org/0000-0001-8503-7125"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":["Information Science and Technology College, Dalian Maritime University, Dalian, China","Information Sci-ence and Technology College, Dalian Maritime University, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Science and Technology College, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]},{"raw_affiliation_string":"Information Sci-ence and Technology College, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100446730","display_name":"Weiwei Zhang","orcid":"https://orcid.org/0000-0001-8445-7398"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiwei Zhang","raw_affiliation_strings":["Information Science and Technology College, Dalian Maritime University, Dalian, China","Information Sci-ence and Technology College, Dalian Maritime University, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0001-8445-7398","affiliations":[{"raw_affiliation_string":"Information Science and Technology College, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]},{"raw_affiliation_string":"Information Sci-ence and Technology College, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035149571","display_name":"Zhaohui Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaohui Zheng","raw_affiliation_strings":["Information Science and Technology College, Dalian Maritime University, Dalian, China","Information Sci-ence and Technology College, Dalian Maritime University, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Science and Technology College, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]},{"raw_affiliation_string":"Information Sci-ence and Technology College, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063170334","display_name":"Mingyang Pan","orcid":"https://orcid.org/0000-0003-1327-6105"},"institutions":[{"id":"https://openalex.org/I43313876","display_name":"Dalian Maritime University","ror":"https://ror.org/002b7nr53","country_code":"CN","type":"education","lineage":["https://openalex.org/I43313876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyang Pan","raw_affiliation_strings":["Navigation College, Dalian Maritime University, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-1327-6105","affiliations":[{"raw_affiliation_string":"Navigation College, Dalian Maritime University, Dalian, China","institution_ids":["https://openalex.org/I43313876"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040711493","display_name":"Rong Wang","orcid":"https://orcid.org/0000-0001-7008-2628"},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Wang","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian Minzu University, Dalian, China","School of Information and Communication Engi-neering, Dalian Minzu University, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian Minzu University, Dalian, China","institution_ids":["https://openalex.org/I61565387"]},{"raw_affiliation_string":"School of Information and Communication Engi-neering, Dalian Minzu University, Dalian, China","institution_ids":["https://openalex.org/I61565387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8335,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76224679,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"70","issue":"3","first_page":"6054","last_page":"6063"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980999827384949,"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":0.9980999827384949,"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/T10860","display_name":"Speech and Audio Processing","score":0.9940999746322632,"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/T11309","display_name":"Music and Audio Processing","score":0.9588000178337097,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.775597333908081},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6483545899391174},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6037515997886658},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5964329242706299},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.49684861302375793},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4410957396030426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2598295211791992},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.21994590759277344},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17137828469276428},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1355385184288025}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.775597333908081},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6483545899391174},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6037515997886658},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5964329242706299},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.49684861302375793},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4410957396030426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2598295211791992},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.21994590759277344},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17137828469276428},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1355385184288025},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tce.2024.3412053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tce.2024.3412053","pdf_url":null,"source":{"id":"https://openalex.org/S126824455","display_name":"IEEE Transactions on Consumer Electronics","issn_l":"0098-3063","issn":["0098-3063","1558-4127"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Consumer Electronics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1082236601","display_name":null,"funder_award_id":"62301109","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1193537047","display_name":null,"funder_award_id":"2020M680932","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G6987529742","display_name":null,"funder_award_id":"52371363","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W29794711","https://openalex.org/W1552314771","https://openalex.org/W2107860279","https://openalex.org/W2133665775","https://openalex.org/W2141998673","https://openalex.org/W2471520273","https://openalex.org/W2545643431","https://openalex.org/W2889244839","https://openalex.org/W2947716587","https://openalex.org/W2963470893","https://openalex.org/W2964243274","https://openalex.org/W3015437531","https://openalex.org/W3034949308","https://openalex.org/W3097514409","https://openalex.org/W3097828251","https://openalex.org/W3144035034","https://openalex.org/W3160427568","https://openalex.org/W3168542456","https://openalex.org/W3187128306","https://openalex.org/W3196760057","https://openalex.org/W3202575900","https://openalex.org/W3204116061","https://openalex.org/W4210682690","https://openalex.org/W4226332109","https://openalex.org/W4281898714","https://openalex.org/W4296068763","https://openalex.org/W4380520419","https://openalex.org/W4384028538","https://openalex.org/W4388018834","https://openalex.org/W4388240223","https://openalex.org/W6631229253","https://openalex.org/W6741832134","https://openalex.org/W6763832098","https://openalex.org/W6767111847","https://openalex.org/W6778823374","https://openalex.org/W6779577414","https://openalex.org/W6779871621","https://openalex.org/W6783382068","https://openalex.org/W6783867762","https://openalex.org/W6785529287","https://openalex.org/W6786325012","https://openalex.org/W6838843145","https://openalex.org/W6846351131","https://openalex.org/W6846732351","https://openalex.org/W6930505429"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W2366752344"],"abstract_inverted_index":{"Though":[0],"singing":[1,26,113,135,168],"voice":[2,169],"synthesis":[3],"(SVS)":[4],"has":[5],"been":[6],"explored":[7],"by":[8],"recent":[9],"works,":[10],"pitch":[11],"over-smoothing":[12],"and":[13,133,170],"spectral":[14],"blurring":[15],"are":[16],"still":[17],"unresolved,":[18],"resulting":[19,71,129],"in":[20,41,48,61,68,72,130],"lack":[21],"of":[22,24,55,110,139],"expressiveness":[23],"the":[25,30,42,52,64,69,79,87,98,103,108,111,117,121,140,155],"voice.":[27,136],"To":[28],"tackle":[29],"afore-mentioned":[31],"problems,":[32],"an":[33],"SVS":[34,104],"model":[35,105],"that":[36,107,154],"adopts":[37],"fine-grained":[38,80],"perception":[39,81],"modeling":[40],"generative":[43],"adversarial":[44],"framework":[45],"is":[46,58,83,143],"proposed":[47,141,156],"this":[49],"work.":[50],"Specifically,":[51],"forward":[53],"difference":[54],"fundamental":[56,66,76,162],"frequency":[57,67],"also":[59],"modeled":[60],"addition":[62],"to":[63,85,89,101],"conventional":[65],"generator,":[70],"more":[73,91,131,160,166],"accurate":[74,161],"vocal":[75],"frequencies.":[77],"Moreover,":[78],"module":[82],"utilized":[84],"restrict":[86],"generator":[88],"focus":[90],"on":[92,145],"detailed":[93],"information.":[94],"Then,":[95],"we":[96],"adopt":[97],"WGAN":[99],"discriminator":[100],"optimize":[102],"such":[106],"distribution":[109],"generated":[112],"spectrogram":[114,122],"effectively":[115],"approximates":[116],"actual":[118],"one.":[119],"Finally,":[120],"was":[123],"fed":[124],"into":[125],"our":[126],"modified":[127],"vocoder,":[128],"expressive":[132],"natural":[134,167],"The":[137],"effectiveness":[138],"approach":[142,157],"verified":[144],"a":[146],"professional":[147],"Mandarin":[148],"Chinese":[149],"corpus.":[150],"Experimental":[151],"results":[152],"demonstrate":[153],"can":[158],"obtain":[159],"frequencies,":[163],"clearer":[164],"spectrograms,":[165],"higher":[171],"mean":[172],"opinion":[173],"score":[174],"(MOS),":[175],"comparing":[176],"with":[177],"several":[178],"state-of-the-art":[179],"approaches.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}
