{"id":"https://openalex.org/W3095787156","doi":"https://doi.org/10.21437/interspeech.2020-1070","title":"Quasi-Periodic Parallel WaveGAN Vocoder: A Non-Autoregressive Pitch-Dependent Dilated Convolution Model for Parametric Speech Generation","display_name":"Quasi-Periodic Parallel WaveGAN Vocoder: A Non-Autoregressive Pitch-Dependent Dilated Convolution Model for Parametric Speech Generation","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095787156","doi":"https://doi.org/10.21437/interspeech.2020-1070","mag":"3095787156"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1070","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5037001032","display_name":"Yi-Chiao Wu","orcid":"https://orcid.org/0000-0003-4390-1354"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi-Chiao Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078778981","display_name":"Tomoki Hayashi","orcid":"https://orcid.org/0000-0001-8782-4093"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoki Hayashi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022943637","display_name":"Takuma Okamoto","orcid":"https://orcid.org/0000-0001-9913-4647"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takuma Okamoto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114514387","display_name":"Hisashi Kawai","orcid":"https://orcid.org/0000-0002-0914-5092"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hisashi Kawai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3535","last_page":"3539"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9954000115394592,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9840999841690063,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6665050387382507},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.664909303188324},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5851016044616699},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5224651098251343},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5146732926368713},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4564206600189209},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4240944981575012},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.37044602632522583},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2938167154788971},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23162713646888733},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17159491777420044},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.08584943413734436}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6665050387382507},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.664909303188324},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5851016044616699},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5224651098251343},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5146732926368713},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4564206600189209},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4240944981575012},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37044602632522583},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2938167154788971},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23162713646888733},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17159491777420044},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.08584943413734436},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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:10.21437/interspeech.2020-1070","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W2161396743","https://openalex.org/W111365173","https://openalex.org/W2386453889","https://openalex.org/W3134790285"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,12,25,45,101],"parallel":[6],"WaveGAN":[7],"(PWG)-like":[8],"neural":[9],"vocoder":[10,46],"with":[11],"quasi-periodic":[13],"(QP)":[14],"architecture":[15],"to":[16,47,121],"improve":[17,122],"the":[18,51,68,75,84,110,116,123,140,152],"pitch":[19,76,111,124,142],"controllability":[20,125],"of":[21,53,78,83,89,94,130,148,160,162],"PWG.":[22,132,164],"PWG":[23,43,62,90,114],"is":[24,35,156],"compact":[26],"non-autoregressive":[27],"(non-AR)":[28],"speech":[29,49,80,95,127,146,150],"generation":[30],"model,":[31],"whose":[32],"generative":[33],"speed":[34],"much":[36],"faster":[37],"than":[38],"real":[39],"time.":[40],"While":[41],"utilizing":[42],"as":[44,57],"generate":[48],"on":[50],"basis":[52],"acoustic":[54,70],"features":[55,71],"such":[56],"spectral":[58],"and":[59,86,126,135,144],"prosodic":[60],"features,":[61],"generates":[63],"high-fidelity":[64],"speech.":[65],"However,":[66],"when":[67,151],"input":[69],"include":[72],"unseen":[73],"pitches,":[74],"accuracy":[77,143],"PWG-generated":[79],"degrades":[81],"because":[82],"fixed":[85],"generic":[87],"network":[88,105,119],"without":[91],"prior":[92],"knowledge":[93],"periodicity.":[96],"The":[97],"proposed":[98],"QPPWG":[99,153],"adopts":[100],"pitch-dependent":[102],"dilated":[103],"convolution":[104],"(PDCNN)":[106],"module,":[107],"which":[108],"introduces":[109],"information":[112],"into":[113],"via":[115],"dynamically":[117],"changed":[118],"architecture,":[120],"modeling":[128],"capability":[129],"vanilla":[131,163],"Both":[133],"objective":[134],"subjective":[136],"evaluation":[137],"results":[138],"show":[139],"higher":[141],"comparable":[145],"quality":[147],"QPPWG-generated":[149],"model":[154],"size":[155],"only":[157],"70":[158],"%":[159],"that":[161]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}