{"id":"https://openalex.org/W3045000780","doi":"https://doi.org/10.1109/taslp.2021.3051765","title":"Quasi-Periodic Parallel WaveGAN: A Non-Autoregressive Raw Waveform Generative Model With Pitch-Dependent Dilated Convolution Neural Network","display_name":"Quasi-Periodic Parallel WaveGAN: A Non-Autoregressive Raw Waveform Generative Model With Pitch-Dependent Dilated Convolution Neural Network","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3045000780","doi":"https://doi.org/10.1109/taslp.2021.3051765","mag":"3045000780"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3051765","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3051765","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9289074/09324976.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/9289074/09324976.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yi-Chiao Wu","orcid":"https://orcid.org/0000-0003-4390-1354"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yi-Chiao Wu","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Aichi, Japan"],"raw_orcid":"https://orcid.org/0000-0003-4390-1354","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tomoki Hayashi","orcid":"https://orcid.org/0000-0001-8782-4093"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Hayashi","raw_affiliation_strings":["Graduate School of Information Science, Nagoya University, Aichi, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8782-4093","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nagoya University, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Takuma Okamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuma Okamoto","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hisashi Kawai","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hisashi Kawai","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":null,"display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Information Technology Center, Nagoya University, Aichi, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8146-1279","affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1837,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.89191955,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"792","last_page":"806"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8203999996185303,"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":0.8203999996185303,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.039900001138448715,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.032600000500679016,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7339000105857849},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6919000148773193},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.6858000159263611},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6248000264167786},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5995000004768372},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5029000043869019},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4478999972343445},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4212000072002411}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7339000105857849},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6919000148773193},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.6858000159263611},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6248000264167786},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6240000128746033},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5995000004768372},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5029000043869019},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49059998989105225},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4478999972343445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4422999918460846},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4212000072002411},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3955000042915344},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C194980680","wikidata":"https://www.wikidata.org/wiki/Q245450","display_name":"Circular convolution","level":5,"score":0.3393999934196472},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27869999408721924},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2590999901294708}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2021.3051765","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3051765","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9289074/09324976.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2007.12955","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.12955","pdf_url":"https://arxiv.org/pdf/2007.12955","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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1109/taslp.2021.3051765","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3051765","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9289074/09324976.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1628655565","display_name":null,"funder_award_id":"JPMJPR1657","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G1688345242","display_name":"Next generation speech translation research","funder_award_id":"17H06101","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G200199876","display_name":"\u30e6\u30fc\u30b6\u306e\u9069\u5fdc\u80fd\u529b\u3092\u6d3b\u7528\u3059\u308b\u5171\u5275\u578b\u97f3\u58f0\u751f\u6210\u6a5f\u80fd\u62e1\u5f35\u6280\u8853\u306e\u69cb\u7bc9","funder_award_id":"JPMJPR1657","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"},{"id":"https://openalex.org/G2521286739","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"},{"id":"https://openalex.org/G2664191106","display_name":"\u97f3\u30e1\u30c7\u30a3\u30a2\u30b3\u30df\u30e5\u30cb\u30b1\u30fc\u30b7\u30e7\u30f3\u306b\u304a\u3051\u308b\u5171\u5275\u578b\u6a5f\u80fd\u62e1\u5f35\u6280\u8853\u306e\u5275\u51fa","funder_award_id":"JPMJCR19A3","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"},{"id":"https://openalex.org/G3497787681","display_name":null,"funder_award_id":"JPMJPR1657","funder_id":"https://openalex.org/F4320338111","funder_display_name":"Precursory Research for Embryonic Science and Technology"},{"id":"https://openalex.org/G6718509927","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8892501299","display_name":null,"funder_award_id":"JPMJCR19A3","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"},{"id":"https://openalex.org/F4320335839","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"},{"id":"https://openalex.org/F4320338111","display_name":"Precursory Research for Embryonic Science and Technology","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3045000780.pdf","grobid_xml":"https://content.openalex.org/works/W3045000780.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W1969526148","https://openalex.org/W2012086895","https://openalex.org/W2049686551","https://openalex.org/W2093450784","https://openalex.org/W2096980176","https://openalex.org/W2099856211","https://openalex.org/W2109189270","https://openalex.org/W2150418026","https://openalex.org/W2151626637","https://openalex.org/W2164764235","https://openalex.org/W2471520273","https://openalex.org/W2601564443","https://openalex.org/W2796495654","https://openalex.org/W2797310469","https://openalex.org/W2803595463","https://openalex.org/W2803714261","https://openalex.org/W2810457573","https://openalex.org/W2890983311","https://openalex.org/W2951310434","https://openalex.org/W2962898107","https://openalex.org/W2963091184","https://openalex.org/W2963175743","https://openalex.org/W2963300588","https://openalex.org/W2963411216","https://openalex.org/W2972333964","https://openalex.org/W2972597685","https://openalex.org/W2972824008","https://openalex.org/W2973115941","https://openalex.org/W2975414524","https://openalex.org/W2990440871","https://openalex.org/W3014786045","https://openalex.org/W3015338123","https://openalex.org/W3015611309","https://openalex.org/W3096429957","https://openalex.org/W3097828251","https://openalex.org/W4235716345","https://openalex.org/W4245284779","https://openalex.org/W6618372016","https://openalex.org/W6631190155","https://openalex.org/W6637242042","https://openalex.org/W6638273328","https://openalex.org/W6639118987","https://openalex.org/W6684821475","https://openalex.org/W6696085341","https://openalex.org/W6732429163","https://openalex.org/W6742995815","https://openalex.org/W6743252760","https://openalex.org/W6743855016","https://openalex.org/W6748140763","https://openalex.org/W6748409065","https://openalex.org/W6750583986","https://openalex.org/W6753855596","https://openalex.org/W6756159577","https://openalex.org/W6767111847","https://openalex.org/W6767164110","https://openalex.org/W6768420517","https://openalex.org/W6771763809","https://openalex.org/W6776594914","https://openalex.org/W6777363790","https://openalex.org/W6781156502","https://openalex.org/W6781692443","https://openalex.org/W6843673214"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,105],"propose":[4],"a":[5,15,20,33,89,107],"quasi-periodic":[6,16],"parallel":[7,21],"WaveGAN":[8,22],"(QPPWG)":[9],"waveform":[10,37],"generative":[11,38],"model,":[12,39],"which":[13,114,173],"applies":[14],"(QP)":[17],"structure":[18,109],"to":[19,112,118,128],"(PWG)":[23],"model":[24,53],"using":[25,180],"pitch-dependent":[26],"dilated":[27],"convolution":[28],"networks":[29],"(PDCNNs).":[30],"PWG":[31,61,146],"is":[32,43,155],"small-footprint":[34],"GAN-based":[35],"raw":[36],"whose":[40],"generation":[41],"time":[42,48],"much":[44],"faster":[45],"than":[46],"real":[47],"because":[49],"of":[50,159,163,171,187],"its":[51],"compact":[52],"and":[54,57,68,101,138,169,177,184],"non-autoregressive":[55],"(non-AR)":[56],"non-causal":[58],"mechanisms.":[59],"Although":[60],"achieves":[62],"high-fidelity":[63],"speech":[64,102],"generation,":[65],"the":[66,98,119,124,129,148,160,181,188],"generic":[67],"simple":[69],"network":[70,120,125],"architecture":[71,126],"lacks":[72],"pitch":[73,99,116],"controllability":[74,100],"for":[75],"an":[76],"unseen":[77],"auxiliary":[78,130,149],"fundamental":[79],"frequency":[80],"(F":[81],"<sub":[82,92,132,151],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[83,93,133,152],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0</sub>":[84,94,134,153],")":[85],"feature":[86,154],"such":[87],"as":[88],"scaled":[90],"F":[91,131,150],".":[95],"To":[96],"improve":[97],"modeling":[103],"capability,":[104],"apply":[106],"QP":[108,189],"with":[110],"PDCNNs":[111],"PWG,":[113],"introduces":[115],"information":[117],"by":[121],"dynamically":[122],"changing":[123],"corresponding":[127],"feature.":[135],"Both":[136],"objective":[137],"subjective":[139],"experimental":[140],"results":[141],"show":[142,166],"that":[143],"QPPWG":[144,164],"outperforms":[145],"when":[147],"scaled.":[156],"Moreover,":[157],"analyses":[158],"intermediate":[161],"outputs":[162],"also":[165],"better":[167],"tractability":[168],"interpretability":[170],"QPPWG,":[172],"respectively":[174],"models":[175],"spectral":[176],"excitation-like":[178],"signals":[179],"cascaded":[182],"fixed":[183],"adaptive":[185],"blocks":[186],"structure.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2020-07-29T00:00:00"}