{"id":"https://openalex.org/W2990440871","doi":"https://doi.org/10.1109/taslp.2019.2956145","title":"Neural Source-Filter Waveform Models for Statistical Parametric Speech Synthesis","display_name":"Neural Source-Filter Waveform Models for Statistical Parametric Speech Synthesis","publication_year":2019,"publication_date":"2019-11-27","ids":{"openalex":"https://openalex.org/W2990440871","doi":"https://doi.org/10.1109/taslp.2019.2956145","mag":"2990440871"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2956145","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2956145","pdf_url":null,"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":null,"license_id":null,"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":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/files/142284938/Neural_source_filter_WANG_DOA16112019_AFV.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100327839","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8246-0606"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8246-0606","affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"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, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, U.K","National Institute of Informatics, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-2752-3955","affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.531,"has_fulltext":true,"cited_by_count":127,"citation_normalized_percentile":{"value":0.98540854,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"28","issue":null,"first_page":"402","last_page":"415"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9973000288009644,"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/waveform","display_name":"Waveform","score":0.87735915184021},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7481318712234497},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6069833636283875},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6051463484764099},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5687814354896545},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.568681538105011},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5144217610359192},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4695364236831665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4309561252593994},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38490042090415955},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3556968569755554},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12724018096923828},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0873359739780426}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.87735915184021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7481318712234497},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6069833636283875},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6051463484764099},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5687814354896545},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.568681538105011},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5144217610359192},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4695364236831665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4309561252593994},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38490042090415955},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3556968569755554},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12724018096923828},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0873359739780426},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2019.2956145","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2956145","pdf_url":null,"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":null,"license_id":null,"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:pure.ed.ac.uk:openaire/ceebfa03-8942-4369-9253-9ae7f948f204","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/ceebfa03-8942-4369-9253-9ae7f948f204","pdf_url":"https://www.research.ed.ac.uk/files/142284938/Neural_source_filter_WANG_DOA16112019_AFV.pdf","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wang, X, Takaki, S & Yamagishi, J 2020, 'Neural Source-Filter Waveform Models for Statistical Parametric Speech Synthesis', IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 28, pp. 402-415. https://doi.org/10.1109/TASLP.2019.2956145","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/ceebfa03-8942-4369-9253-9ae7f948f204","is_oa":true,"landing_page_url":"https://ieeexplore.ieee.org/abstract/document/8915761","pdf_url":"http://hdl.handle.net/20.500.11820/ceebfa03-8942-4369-9253-9ae7f948f204","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wang, X, Takaki, S & Yamagishi, J 2020, 'Neural Source-Filter Waveform Models for Statistical Parametric Speech Synthesis', IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 28, pp. 402-415. https://doi.org/10.1109/TASLP.2019.2956145","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/ceebfa03-8942-4369-9253-9ae7f948f204","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/ceebfa03-8942-4369-9253-9ae7f948f204","pdf_url":"https://www.research.ed.ac.uk/files/142284938/Neural_source_filter_WANG_DOA16112019_AFV.pdf","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wang, X, Takaki, S & Yamagishi, J 2020, 'Neural Source-Filter Waveform Models for Statistical Parametric Speech Synthesis', IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 28, pp. 402-415. https://doi.org/10.1109/TASLP.2019.2956145","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3680276803","display_name":"Articulatory text-to-speech synthesis based on digital waveguide mesh driven by deep neural network","funder_award_id":"17K20004","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5028306015","display_name":"One model for all sounds: fast and high-quality neural source-filter model for speech and non-speech waveform modeling","funder_award_id":"19K24371","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6299358200","display_name":"PRISM: Speech privacy preservation based on selecting masking","funder_award_id":"18H04112","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6954941931","display_name":"Communication System for Defending against Attacks of Media Clones","funder_award_id":"16H06302","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7623259429","display_name":"Robust voice cloning technologies in noisy environments and its applications","funder_award_id":"17H04687","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2990440871.pdf","grobid_xml":"https://content.openalex.org/works/W2990440871.grobid-xml"},"referenced_works_count":85,"referenced_works":["https://openalex.org/W95551363","https://openalex.org/W136252730","https://openalex.org/W304834817","https://openalex.org/W1480958225","https://openalex.org/W1496971974","https://openalex.org/W1498609987","https://openalex.org/W1522301498","https://openalex.org/W1570629387","https://openalex.org/W1916501714","https://openalex.org/W1976313025","https://openalex.org/W2003513484","https://openalex.org/W2016589492","https://openalex.org/W2049711495","https://openalex.org/W2063538858","https://openalex.org/W2068247585","https://openalex.org/W2102003408","https://openalex.org/W2109114466","https://openalex.org/W2109189270","https://openalex.org/W2111284386","https://openalex.org/W2120847449","https://openalex.org/W2128395221","https://openalex.org/W2129142580","https://openalex.org/W2135029798","https://openalex.org/W2144499799","https://openalex.org/W2157621600","https://openalex.org/W2194775991","https://openalex.org/W2294797155","https://openalex.org/W2394921947","https://openalex.org/W2402121493","https://openalex.org/W2405144467","https://openalex.org/W2471520273","https://openalex.org/W2513112113","https://openalex.org/W2519091744","https://openalex.org/W2549013258","https://openalex.org/W2559246505","https://openalex.org/W2584032004","https://openalex.org/W2587284713","https://openalex.org/W2595110011","https://openalex.org/W2748565458","https://openalex.org/W2749881488","https://openalex.org/W2769810959","https://openalex.org/W2801291345","https://openalex.org/W2801493797","https://openalex.org/W2803595463","https://openalex.org/W2886022419","https://openalex.org/W2890983311","https://openalex.org/W2902681596","https://openalex.org/W2949382160","https://openalex.org/W2963090522","https://openalex.org/W2963091184","https://openalex.org/W2963154580","https://openalex.org/W2963175743","https://openalex.org/W2963299674","https://openalex.org/W2963300588","https://openalex.org/W2963522141","https://openalex.org/W2963589210","https://openalex.org/W2963782041","https://openalex.org/W2963945466","https://openalex.org/W2963975282","https://openalex.org/W2964121744","https://openalex.org/W2964307104","https://openalex.org/W3143596294","https://openalex.org/W4251164127","https://openalex.org/W4294619240","https://openalex.org/W4298580827","https://openalex.org/W4298642009","https://openalex.org/W6603921752","https://openalex.org/W6605536571","https://openalex.org/W6610566761","https://openalex.org/W6631190155","https://openalex.org/W6639972086","https://openalex.org/W6675380101","https://openalex.org/W6680012447","https://openalex.org/W6681794868","https://openalex.org/W6696843773","https://openalex.org/W6712208827","https://openalex.org/W6713153552","https://openalex.org/W6729703263","https://openalex.org/W6732429163","https://openalex.org/W6733471323","https://openalex.org/W6748409065","https://openalex.org/W6753855596","https://openalex.org/W6756686980","https://openalex.org/W6832800064","https://openalex.org/W6844105982"],"related_works":["https://openalex.org/W1974895211","https://openalex.org/W2176409448","https://openalex.org/W2129841057","https://openalex.org/W3040712279","https://openalex.org/W2364769705","https://openalex.org/W4367555392","https://openalex.org/W2374664672","https://openalex.org/W2056136368","https://openalex.org/W2538520412","https://openalex.org/W2039489009"],"abstract_inverted_index":{"Neural":[0],"waveform":[1,32,41,59,98],"models":[2,49,184,205],"have":[3],"demonstrated":[4,201],"better":[5],"performance":[6],"than":[7,213],"conventional":[8],"vocoders":[9],"for":[10,151,162],"statistical":[11],"parametric":[12],"speech":[13,222,239],"synthesis.":[14],"One":[15],"of":[16,31,70,81,219],"the":[17,29,136,147,152,186,203,217,220,224],"best":[18,225],"models,":[19],"called":[20],"WaveNet,":[21],"uses":[22],"an":[23,85,176],"autoregressive":[24],"(AR)":[25],"approach":[26],"to":[27,38,87,104,108,116,230],"model":[28,76,163,227],"distribution":[30],"sampling":[33],"points,":[34],"but":[35,64],"it":[36],"has":[37],"generate":[39,56,109,117],"a":[40,43,57,61,67,74,79,94,119,124,129,139,142,235],"in":[42,60],"time-consuming":[44],"sequential":[45],"manner.":[46],"Some":[47],"new":[48],"that":[50,101,122,134,145,202,231],"use":[51],"inverse-autoregressive":[52],"flow":[53],"(IAF)":[54],"can":[55,166],"whole":[58],"one-shot":[62],"manner":[63],"require":[65],"either":[66],"larger":[68],"amount":[69],"training":[71,82],"time":[72],"or":[73],"complicated":[75],"architecture":[77],"plus":[78],"blend":[80],"criteria.":[83],"As":[84,175],"alternative":[86],"AR":[88],"and":[89,106,141,154,189,216],"IAF-based":[90],"frameworks,":[91],"we":[92,180],"propose":[93],"neural":[95],"source-filter":[96],"(NSF)":[97],"modeling":[99],"framework":[100,112,158,188],"is":[102],"straightforward":[103],"train":[105],"fast":[107],"waveforms.":[110],"This":[111,157],"requires":[113],"three":[114,182],"components":[115],"waveforms:":[118],"source":[120,153],"module":[121,133,144],"generates":[123],"sine-based":[125],"signal":[126],"as":[127],"excitation,":[128],"non-AR":[130],"dilated-convolution-based":[131],"filter":[132,155],"transforms":[135],"excitation":[137],"into":[138],"waveform,":[140],"conditional":[143],"pre-processes":[146],"input":[148],"acoustic":[149],"features":[150],"modules.":[156],"minimizes":[159],"spectral-amplitude":[160],"distances":[161],"training,":[164],"which":[165],"be":[167],"efficiently":[168],"implemented":[169],"using":[170,194],"short-time":[171],"Fourier":[172],"transform":[173],"routines.":[174],"initial":[177],"NSF":[178,183,204,226],"study,":[179],"designed":[181],"under":[185],"proposed":[187],"compared":[190],"them":[191],"with":[192],"WaveNet":[193,233],"our":[195,214],"deep":[196],"learning":[197],"toolkit.":[198],"It":[199],"was":[200,228],"generated":[206],"waveforms":[207],"at":[208],"least":[209],"100":[210],"times":[211],"faster":[212],"WaveNet-vocoder,":[215],"quality":[218],"synthetic":[221],"from":[223,232],"comparable":[229],"on":[234],"large":[236],"single-speaker":[237],"Japanese":[238],"corpus.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}