{"id":"https://openalex.org/W3162536450","doi":"https://doi.org/10.1109/icassp39728.2021.9414401","title":"Periodnet: A Non-Autoregressive Waveform Generation Model with a Structure Separating Periodic and Aperiodic Components","display_name":"Periodnet: A Non-Autoregressive Waveform Generation Model with a Structure Separating Periodic and Aperiodic Components","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162536450","doi":"https://doi.org/10.1109/icassp39728.2021.9414401","mag":"3162536450"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414401","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5086910479","display_name":"Yukiya Hono","orcid":"https://orcid.org/0000-0003-1245-8791"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yukiya Hono","raw_affiliation_strings":["Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062895056","display_name":"Shinji Takaki","orcid":"https://orcid.org/0000-0001-7294-7699"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinji Takaki","raw_affiliation_strings":["Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067594810","display_name":"Kei Hashimoto","orcid":"https://orcid.org/0000-0003-2081-0396"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kei Hashimoto","raw_affiliation_strings":["Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049909008","display_name":"Keiichiro Oura","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichiro Oura","raw_affiliation_strings":["Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023240652","display_name":"Yoshihiko Nankaku","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshihiko Nankaku","raw_affiliation_strings":["Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103023678","display_name":"Keiichi Tokuda","orcid":"https://orcid.org/0000-0001-6143-0133"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichi Tokuda","raw_affiliation_strings":["Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Department of Computer Science,Nagoya,Japan","institution_ids":["https://openalex.org/I197274945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197274945"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6049","last_page":"6053"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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":0.9988999962806702,"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/aperiodic-graph","display_name":"Aperiodic graph","score":0.922095775604248},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.870489776134491},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8022171258926392},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6720057725906372},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.634432315826416},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5832441449165344},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4355664551258087},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4272480607032776},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13435444235801697},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10418429970741272},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06781005859375},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.06726959347724915}],"concepts":[{"id":"https://openalex.org/C104247578","wikidata":"https://www.wikidata.org/wiki/Q4779368","display_name":"Aperiodic graph","level":2,"score":0.922095775604248},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.870489776134491},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8022171258926392},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6720057725906372},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.634432315826416},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5832441449165344},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4355664551258087},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4272480607032776},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13435444235801697},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10418429970741272},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06781005859375},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.06726959347724915},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414401","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2049686551","https://openalex.org/W2088432713","https://openalex.org/W2099471712","https://openalex.org/W2152905683","https://openalex.org/W2284050935","https://openalex.org/W2405756170","https://openalex.org/W2471520273","https://openalex.org/W2515336442","https://openalex.org/W2519091744","https://openalex.org/W2587284713","https://openalex.org/W2749651610","https://openalex.org/W2769810959","https://openalex.org/W2921576841","https://openalex.org/W2940405045","https://openalex.org/W2949382160","https://openalex.org/W2962882868","https://openalex.org/W2963091184","https://openalex.org/W2963300588","https://openalex.org/W2963685250","https://openalex.org/W2963691546","https://openalex.org/W2963971656","https://openalex.org/W2963975282","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2968917279","https://openalex.org/W2970006822","https://openalex.org/W2972504514","https://openalex.org/W2990440871","https://openalex.org/W2994689640","https://openalex.org/W3015338123","https://openalex.org/W3120896524","https://openalex.org/W4289305009","https://openalex.org/W4294619240","https://openalex.org/W4298580827","https://openalex.org/W4320013936","https://openalex.org/W6683091923","https://openalex.org/W6695676441","https://openalex.org/W6713645886","https://openalex.org/W6733471323","https://openalex.org/W6748409065","https://openalex.org/W6749489859","https://openalex.org/W6753855596","https://openalex.org/W6756159577","https://openalex.org/W6767111847","https://openalex.org/W6767164110","https://openalex.org/W6788806912"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W1984347656","https://openalex.org/W2535215250","https://openalex.org/W2024201202"],"abstract_inverted_index":{"We":[0,145],"propose":[1,87],"PeriodNet,":[2],"a":[3,10,38,47,63,76,88,92,129,153],"non-autoregressive":[4],"(non-AR)":[5],"waveform":[6,25,49,79],"generation":[7,26],"model":[8,12,90,94],"with":[9,152,164],"new":[11],"structure":[13,95,137],"for":[14],"modeling":[15],"periodic":[16,51,97,110],"and":[17,33,52,91,98,111,118],"aperiodic":[18,53,99,112],"components":[19,56,74],"in":[20,80,125],"speech":[21,30,39,48,65,78,150],"waveforms.":[22],"The":[23,101],"non-AR":[24],"models":[27,106],"can":[28,34,161],"generate":[29,62],"waveforms":[31,151],"parallelly":[32],"be":[35,58,162],"used":[36],"as":[37,116],"vocoder":[40],"by":[41],"conditioning":[42],"an":[43],"acoustic":[44],"feature.":[45],"Since":[46],"contains":[50],"components,":[54],"both":[55],"should":[57],"appropriately":[59],"modeled":[60],"to":[61,71],"high-quality":[64],"waveform.":[66,144],"However,":[67],"it":[68],"is":[69,122],"difficult":[70],"decompose":[72],"the":[73,139,142,149,157],"from":[75],"natural":[77],"advance.":[81],"To":[82],"address":[83],"this":[84],"issue,":[85],"we":[86],"parallel":[89],"series":[93],"separating":[96],"components.":[100],"features":[102],"of":[103,141,156],"our":[104,135],"proposed":[105,136],"are":[107,114],"that":[108,134,148],"explicit":[109],"signals":[113],"taken":[115],"input,":[117],"external":[119],"periodic/aperiodic":[120],"decomposition":[121],"not":[123],"needed":[124],"training.":[126],"Experiments":[127],"using":[128],"singing":[130],"voice":[131],"corpus":[132],"show":[133,147],"improves":[138],"naturalness":[140],"generated":[143,163],"also":[146],"pitch":[154],"outside":[155],"training":[158],"data":[159],"range":[160],"more":[165],"naturalness.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}