{"id":"https://openalex.org/W3011892665","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023357","title":"Non-parallel Many-to-many Singing Voice Conversion by Adversarial Learning","display_name":"Non-parallel Many-to-many Singing Voice Conversion by Adversarial Learning","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3011892665","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023357","mag":"3011892665"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5010760273","display_name":"Jinsen Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinsen Hu","raw_affiliation_strings":["College of Mathematics and Computer Science, Fuzhou University, China"],"affiliations":[{"raw_affiliation_string":"College of Mathematics and Computer Science, Fuzhou University, China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100624941","display_name":"Chunyan Yu","orcid":"https://orcid.org/0000-0002-9260-6629"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyan Yu","raw_affiliation_strings":["College of Mathematics and Computer Science, Fuzhou University, China"],"affiliations":[{"raw_affiliation_string":"College of Mathematics and Computer Science, Fuzhou University, China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010472148","display_name":"Faqian Guan","orcid":"https://orcid.org/0000-0002-5701-8311"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Faqian Guan","raw_affiliation_strings":["College of Mathematics and Computer Science, Fuzhou University, China"],"affiliations":[{"raw_affiliation_string":"College of Mathematics and Computer Science, Fuzhou University, China","institution_ids":["https://openalex.org/I80947539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010760273"],"corresponding_institution_ids":["https://openalex.org/I80947539"],"apc_list":null,"apc_paid":null,"fwci":0.4976,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65686756,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"110","issue":null,"first_page":"125","last_page":"132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9987999796867371,"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/adversarial-system","display_name":"Adversarial system","score":0.7777286171913147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7355334758758545},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7339649796485901},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5955750346183777},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3149513006210327},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.13187268376350403}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7777286171913147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7355334758758545},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7339649796485901},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5955750346183777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3149513006210327},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.13187268376350403},{"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/apsipaasc47483.2019.9023357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1482298176","https://openalex.org/W1590808459","https://openalex.org/W1836465849","https://openalex.org/W2007023536","https://openalex.org/W2099471712","https://openalex.org/W2120605154","https://openalex.org/W2156142001","https://openalex.org/W2294038178","https://openalex.org/W2401296648","https://openalex.org/W2471520273","https://openalex.org/W2473388484","https://openalex.org/W2502312327","https://openalex.org/W2532494225","https://openalex.org/W2583165630","https://openalex.org/W2604509013","https://openalex.org/W2608338293","https://openalex.org/W2612434969","https://openalex.org/W2746265435","https://openalex.org/W2747238065","https://openalex.org/W2763280966","https://openalex.org/W2774707525","https://openalex.org/W2792263949","https://openalex.org/W2804078698","https://openalex.org/W2811135961","https://openalex.org/W2888922217","https://openalex.org/W2888982879","https://openalex.org/W2889457963","https://openalex.org/W2902070858","https://openalex.org/W2949117887","https://openalex.org/W2953030256","https://openalex.org/W2962793481","https://openalex.org/W2963073614","https://openalex.org/W2963767194","https://openalex.org/W2963830550","https://openalex.org/W4320013936","https://openalex.org/W6628615481","https://openalex.org/W6635429420","https://openalex.org/W6638667902","https://openalex.org/W6651827963","https://openalex.org/W6697024540","https://openalex.org/W6712902469","https://openalex.org/W6724804524","https://openalex.org/W6737196085","https://openalex.org/W6737575990","https://openalex.org/W6746914816","https://openalex.org/W6749927861","https://openalex.org/W6752378368","https://openalex.org/W6753055032"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2502115930","https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W2366077683"],"abstract_inverted_index":{"With":[0],"the":[1,71,79,87,97,110,121,129,136],"rapid":[2],"development":[3],"of":[4,73],"deep":[5,20],"learning,":[6],"although":[7],"speech":[8,131],"conversion":[9,42,66],"had":[10],"made":[11],"great":[12],"progress,":[13],"there":[14],"are":[15],"still":[16],"rare":[17],"researches":[18],"in":[19],"learning":[21,59],"to":[22,92,105],"model":[23,75,88,119],"on":[24,32,96,128,135],"singing":[25,64,138],"voice":[26,65],"conversion,":[27],"which":[28,82],"is":[29,51,76,103],"mainly":[30],"based":[31],"statistical":[33],"methods":[34],"at":[35],"present":[36],"and":[37,112,124],"can":[38],"only":[39,127],"achieve":[40],"one-to-one":[41],"with":[43],"parallel":[44,130],"training":[45],"datasets.":[46,69],"So":[47],"far,":[48],"its":[49],"application":[50],"limited.":[52],"This":[53],"paper":[54],"proposes":[55],"a":[56],"generative":[57],"adversarial":[58],"model,":[60],"MSVC-GAN,":[61],"for":[62],"many-to-many":[63],"using":[67],"non-parallel":[68,137],"First,":[70],"generator":[72],"our":[74,118],"concatenated":[77],"by":[78],"singer":[80],"label,":[81],"denotes":[83],"domain":[84],"constraint.":[85],"Furthermore,":[86],"integrates":[89],"self-attention":[90],"mechanism":[91],"capture":[93],"long-term":[94],"dependence":[95],"spectral":[98],"features.":[99],"Finally,":[100],"switchable":[101],"normalization":[102],"employed":[104],"stabilize":[106],"network":[107],"training.":[108],"Both":[109],"objective":[111],"subjective":[113],"evaluation":[114],"results":[115],"show":[116],"that":[117],"achieves":[120],"highest":[122],"similarity":[123],"naturalness":[125],"not":[126],"dataset":[132],"but":[133],"also":[134],"dataset.":[139]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}