{"id":"https://openalex.org/W3007100714","doi":"https://doi.org/10.1587/transinf.2019edp7228","title":"Generative Moment Matching Network-Based Neural Double-Tracking for Synthesized and Natural Singing Voices","display_name":"Generative Moment Matching Network-Based Neural Double-Tracking for Synthesized and Natural Singing Voices","publication_year":2020,"publication_date":"2020-02-29","ids":{"openalex":"https://openalex.org/W3007100714","doi":"https://doi.org/10.1587/transinf.2019edp7228","mag":"3007100714"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2019edp7228","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edp7228","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/3/E103.D_2019EDP7228/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/3/E103.D_2019EDP7228/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066687140","display_name":"Hiroki Tamaru","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hiroki TAMARU","raw_affiliation_strings":["The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083394213","display_name":"Yuki Saito","orcid":"https://orcid.org/0000-0002-7967-2613"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki SAITO","raw_affiliation_strings":["The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinnosuke TAKAMICHI","raw_affiliation_strings":["The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024181978","display_name":"Tomoki Koriyama","orcid":"https://orcid.org/0000-0002-8347-5604"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki KORIYAMA","raw_affiliation_strings":["The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi SARUWATARI","raw_affiliation_strings":["The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5066687140"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.6061,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.64733377,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"E103.D","issue":"3","first_page":"639","last_page":"647"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.8534101247787476},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.8440800905227661},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6894787549972534},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.6734446287155151},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6456417441368103},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4906882047653198},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.48820072412490845},{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.4754970967769623},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.41894787549972534},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.414361834526062},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.41147157549858093},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3576212227344513},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3492342233657837},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3261438012123108},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15115207433700562},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.07914921641349792}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8534101247787476},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8440800905227661},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6894787549972534},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.6734446287155151},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6456417441368103},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4906882047653198},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.48820072412490845},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.4754970967769623},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.41894787549972534},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.414361834526062},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.41147157549858093},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3576212227344513},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3492342233657837},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3261438012123108},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15115207433700562},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.07914921641349792},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","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:10.1587/transinf.2019edp7228","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edp7228","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/3/E103.D_2019EDP7228/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2019edp7228","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edp7228","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/3/E103.D_2019EDP7228/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322525","display_name":"Secom Science and Technology Foundation","ror":"https://ror.org/05ggzej07"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3007100714.pdf","grobid_xml":"https://content.openalex.org/works/W3007100714.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W29794711","https://openalex.org/W620379668","https://openalex.org/W1487641199","https://openalex.org/W2029434926","https://openalex.org/W2099471712","https://openalex.org/W2124097505","https://openalex.org/W2144902422","https://openalex.org/W2146502635","https://openalex.org/W2146641075","https://openalex.org/W2154920538","https://openalex.org/W2293049663","https://openalex.org/W2395578248","https://openalex.org/W2408435475","https://openalex.org/W2428952132","https://openalex.org/W2471520273","https://openalex.org/W2515336442","https://openalex.org/W2519648275","https://openalex.org/W2567070169","https://openalex.org/W2746654391","https://openalex.org/W2778460379","https://openalex.org/W2787685498","https://openalex.org/W2804998325","https://openalex.org/W2951004968","https://openalex.org/W2962916039","https://openalex.org/W2963398683","https://openalex.org/W2963568710","https://openalex.org/W2964286535","https://openalex.org/W2973166267","https://openalex.org/W4247639588"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W2280377497","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W3174044702","https://openalex.org/W2967848559","https://openalex.org/W4283803360"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,33,45,86,150,176,209],"generative":[4],"moment":[5],"matching":[6],"network":[7],"(GMMN)-based":[8],"post-filtering":[9,177],"method":[10,27,88,153,178,198,219],"for":[11,179],"providing":[12],"inter-utterance":[13,56,127,139,201,224],"pitch":[14,202],"variation":[15,84,128,140,203,225],"to":[16,23,106,109,121,158,226,242],"singing":[17,110,115,160,185,206,228,247],"voices":[18,186,207,229],"and":[19,37,63,222,230,245],"discusses":[20],"its":[21],"application":[22],"our":[24,197,233],"developed":[25],"mixing":[26,87],"called":[28,55,89,154],"neural":[29],"double-tracking":[30,90],"(NDT).":[31],"When":[32],"human":[34,205],"singer":[35,190],"sings":[36],"records":[38],"the":[39,48,59,64,80,94,101,130,162,189,200,217],"same":[40,81,95],"song":[41],"twice,":[42,99],"there":[43,124,148],"is":[44,54,97,125,133,136,145,149],"difference":[46],"between":[47],"two":[49,102],"recordings.":[50],"The":[51,193],"difference,":[52],"which":[53,117],"variation,":[57],"enriches":[58],"performer's":[60],"musical":[61],"expression":[62],"audience's":[65],"experience.":[66],"For":[67],"example,":[68],"it":[69,75],"makes":[70],"every":[71],"concert":[72],"special":[73],"because":[74,129],"never":[76],"recurs":[77],"in":[78,113,166],"exactly":[79],"manner.":[82],"Inter-utterance":[83],"enables":[85],"(DT).":[91],"With":[92],"DT,":[93],"phrase":[96],"recorded":[98],"then":[100],"recordings":[103],"are":[104,118],"mixed":[105],"give":[107],"richness":[108],"voices.":[111,248],"However,":[112],"synthesized":[114,182,227,244],"voices,":[116,161],"commonly":[119],"used":[120],"create":[122],"music,":[123],"no":[126,138],"synthesis":[131],"process":[132],"deterministic.":[134],"There":[135],"also":[137],"when":[141,240],"only":[142],"one":[143],"voice":[144],"recorded.":[146],"Although":[147],"signal":[151,163],"processing-based":[152],"artificial":[155],"DT":[156],"(ADT)":[157],"layer":[159],"processing":[164],"results":[165,213],"unnatural":[167],"sound":[168],"artifacts.":[169],"To":[170],"solve":[171],"these":[172],"problems,":[173],"we":[174],"propose":[175],"randomly":[180],"modulating":[181],"or":[183],"natural":[184,223,246],"as":[187],"if":[188],"sang":[191],"again.":[192],"post-filter":[194],"built":[195],"with":[196],"models":[199],"of":[204],"using":[208],"conditional":[210],"GMMN.":[211],"Evaluation":[212],"indicate":[214],"that":[215,231],"1)":[216],"proposed":[218],"provides":[220],"perceptible":[221],"2)":[232],"NDT":[234],"exhibits":[235],"higher":[236],"double-trackedness":[237],"than":[238],"ADT":[239],"applied":[241],"both":[243]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
