{"id":"https://openalex.org/W4223645605","doi":"https://doi.org/10.1109/iceic54506.2022.9748530","title":"Linear Prediction-based Parallel WaveGAN Speech Synthesis","display_name":"Linear Prediction-based Parallel WaveGAN Speech Synthesis","publication_year":2022,"publication_date":"2022-02-06","ids":{"openalex":"https://openalex.org/W4223645605","doi":"https://doi.org/10.1109/iceic54506.2022.9748530"},"language":"en","primary_location":{"id":"doi:10.1109/iceic54506.2022.9748530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iceic54506.2022.9748530","pdf_url":null,"source":{"id":"https://openalex.org/S4363608213","display_name":"2022 International Conference on Electronics, Information, and Communication (ICEIC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Electronics, Information, and Communication (ICEIC)","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/A5073244533","display_name":"Min-Jae Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Min-Jae Hwang","raw_affiliation_strings":["NAVER Corp.,Seongnam,Korea","NAVER Corp., Seongnam, Korea"],"affiliations":[{"raw_affiliation_string":"NAVER Corp.,Seongnam,Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"NAVER Corp., Seongnam, Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032657615","display_name":"Hyun-Wook Yoon","orcid":"https://orcid.org/0000-0002-2849-4140"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyun-Wook Yoon","raw_affiliation_strings":["NAVER Corp.,Seongnam,Korea","NAVER Corp., Seongnam, Korea"],"affiliations":[{"raw_affiliation_string":"NAVER Corp.,Seongnam,Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"NAVER Corp., Seongnam, Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103612604","display_name":"Chanho Song","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chan-Ho Song","raw_affiliation_strings":["NAVER Corp.,Seongnam,Korea","NAVER Corp., Seongnam, Korea"],"affiliations":[{"raw_affiliation_string":"NAVER Corp.,Seongnam,Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"NAVER Corp., Seongnam, Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033037115","display_name":"Jinseob Kim","orcid":"https://orcid.org/0000-0002-9403-605X"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jin-Seob Kim","raw_affiliation_strings":["NAVER Corp.,Seongnam,Korea","NAVER Corp., Seongnam, Korea"],"affiliations":[{"raw_affiliation_string":"NAVER Corp.,Seongnam,Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"NAVER Corp., Seongnam, Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101480212","display_name":"Jae-Min Kim","orcid":"https://orcid.org/0000-0001-9309-9369"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jae-Min Kim","raw_affiliation_strings":["NAVER Corp.,Seongnam,Korea","NAVER Corp., Seongnam, Korea"],"affiliations":[{"raw_affiliation_string":"NAVER Corp.,Seongnam,Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"NAVER Corp., Seongnam, Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104035145","display_name":"Eunwoo Song","orcid":"https://orcid.org/0000-0003-0642-7083"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Eunwoo Song","raw_affiliation_strings":["NAVER Corp.,Seongnam,Korea","NAVER Corp., Seongnam, Korea"],"affiliations":[{"raw_affiliation_string":"NAVER Corp.,Seongnam,Korea","institution_ids":["https://openalex.org/I60922564"]},{"raw_affiliation_string":"NAVER Corp., Seongnam, Korea","institution_ids":["https://openalex.org/I60922564"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5073244533"],"corresponding_institution_ids":["https://openalex.org/I60922564"],"apc_list":null,"apc_paid":null,"fwci":0.2079,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.37071752,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"2020","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9987000226974487,"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/T11309","display_name":"Music and Audio Processing","score":0.9873999953269958,"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/computer-science","display_name":"Computer science","score":0.7707731127738953},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6888664960861206},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6800439953804016},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6496832370758057},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.6437471508979797},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6424959897994995},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5865781307220459},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5620321035385132},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5381918549537659},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.4928445816040039},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42838308215141296},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4235588610172272},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4207164943218231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31529664993286133},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.133157879114151},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06224912405014038},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.062225162982940674}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7707731127738953},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6888664960861206},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6800439953804016},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6496832370758057},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.6437471508979797},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6424959897994995},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5865781307220459},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5620321035385132},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5381918549537659},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.4928445816040039},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42838308215141296},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4235588610172272},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4207164943218231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31529664993286133},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.133157879114151},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06224912405014038},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.062225162982940674},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iceic54506.2022.9748530","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iceic54506.2022.9748530","pdf_url":null,"source":{"id":"https://openalex.org/S4363608213","display_name":"2022 International Conference on Electronics, Information, and Communication (ICEIC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Electronics, Information, and Communication (ICEIC)","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":26,"referenced_works":["https://openalex.org/W136252730","https://openalex.org/W1557133539","https://openalex.org/W2102003408","https://openalex.org/W2109114466","https://openalex.org/W2284050935","https://openalex.org/W2497720771","https://openalex.org/W2519091744","https://openalex.org/W2535388113","https://openalex.org/W2751205669","https://openalex.org/W2902681596","https://openalex.org/W2963091184","https://openalex.org/W2968917279","https://openalex.org/W2972597685","https://openalex.org/W2984862052","https://openalex.org/W2990440871","https://openalex.org/W3015338123","https://openalex.org/W3132610022","https://openalex.org/W3141224548","https://openalex.org/W3160326269","https://openalex.org/W3196969505","https://openalex.org/W4320013936","https://openalex.org/W6605536571","https://openalex.org/W6675380101","https://openalex.org/W6695676441","https://openalex.org/W6756686980","https://openalex.org/W6791147002"],"related_works":["https://openalex.org/W2082000062","https://openalex.org/W2020989338","https://openalex.org/W2058733683","https://openalex.org/W953964455","https://openalex.org/W2150243332","https://openalex.org/W2010642486","https://openalex.org/W4234201046","https://openalex.org/W2147126679","https://openalex.org/W1823617068","https://openalex.org/W4300049944"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,12,27,58,64,69,84,92],"linear":[4],"prediction":[5],"(LP)-based":[6],"neural":[7],"speech":[8,50,73,93,133,155],"synthesis":[9,54,61,98],"method":[10,62],"for":[11,63],"Parallel":[13],"WaveGAN":[14],"(PWG)":[15],"framework.":[16,66],"A":[17],"recently":[18],"proposed":[19,77,147],"PWG":[20,65,78],"vocoder":[21],"successfully":[22],"generates":[23],"waveform":[24],"sequences":[25],"using":[26,95],"fast":[28],"non-autoregressive":[29],"Wave":[30],"Net":[31],"model.":[32],"However,":[33],"it":[34,103],"often":[35],"suffers":[36],"from":[37,91],"noisy":[38],"outputs":[39],"because":[40],"of":[41,49,72,83,111,130,153],"difficulties":[42],"in":[43],"capturing":[44],"the":[45,76,81,96,109,117,120,128,131,146],"complicated":[46],"time-varying":[47],"nature":[48],"signals.":[51],"To":[52],"improve":[53],"quality,":[55],"we":[56],"introduce":[57],"back-propagable":[59],"LP":[60,97],"Based":[67],"on":[68],"source-filter":[70],"theory":[71],"production":[74],"model,":[75],"model":[79],"learns":[80],"behavior":[82],"source":[85,122],"excitation":[86,113],"signal,":[87],"which":[88],"is":[89,104],"decoupled":[90],"signal":[94,114,134],"filter.":[99,126],"In":[100],"this":[101],"way,":[102],"possible":[105],"to":[106],"separately":[107],"train":[108],"characteristics":[110],"only":[112],"while":[115],"considering":[116],"interaction":[118],"between":[119],"vocal":[121,124],"and":[123,140],"tract":[125],"Thus,":[127],"quality":[129,152],"synthesized":[132],"can":[135],"be":[136],"further":[137],"improved.":[138],"Objective":[139],"subjective":[141],"evaluation":[142],"results":[143],"verified":[144],"that":[145],"methods":[148],"reconstruct":[149],"significantly":[150],"better":[151],"synthetic":[154],"than":[156],"conventional":[157],"methods.":[158]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}