{"id":"https://openalex.org/W3086073551","doi":"https://doi.org/10.1007/s11042-020-09783-9","title":"Noise and acoustic modeling with waveform generator in text-to-speech and neutral speech conversion","display_name":"Noise and acoustic modeling with waveform generator in text-to-speech and neutral speech conversion","publication_year":2020,"publication_date":"2020-09-10","ids":{"openalex":"https://openalex.org/W3086073551","doi":"https://doi.org/10.1007/s11042-020-09783-9","mag":"3086073551"},"language":"en","primary_location":{"id":"doi:10.1007/s11042-020-09783-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-020-09783-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-020-09783-9.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11042-020-09783-9.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086670617","display_name":"Mohammed Salah Al-Radhi","orcid":"https://orcid.org/0000-0003-3094-6916"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Mohammed Salah Al-Radhi","raw_affiliation_strings":["Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016031960","display_name":"Tam\u00e1s G\u00e1bor Csap\u00f3","orcid":"https://orcid.org/0000-0003-4375-7524"},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]},{"id":"https://openalex.org/I2802350943","display_name":"ELTE Hungarian Research Centre for Linguistics","ror":"https://ror.org/005cqsz63","country_code":"HU","type":"facility","lineage":["https://openalex.org/I2802350943"]},{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Tam\u00e1s G\u00e1bor Csap\u00f3","raw_affiliation_strings":["Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary","MTA-ELTE Lend\u00fclet Lingual Articulation Research Group, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]},{"raw_affiliation_string":"MTA-ELTE Lend\u00fclet Lingual Articulation Research Group, Budapest, Hungary","institution_ids":["https://openalex.org/I2802350943","https://openalex.org/I106118109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069988513","display_name":"G\u00e9za N\u00e9meth","orcid":"https://orcid.org/0000-0002-2311-4858"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"G\u00e9za N\u00e9meth","raw_affiliation_strings":["Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5086670617"],"corresponding_institution_ids":["https://openalex.org/I29770179"],"apc_list":null,"apc_paid":null,"fwci":0.2718,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.6471692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"80","issue":"2","first_page":"1969","last_page":"1994"},"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":0.9993000030517578,"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":0.9965000152587891,"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":0.8635910749435425},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7021480798721313},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5483019948005676},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5092185735702515},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5067635178565979},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.482713907957077},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.47140100598335266},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4543541669845581},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3406044840812683},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3125467896461487},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0774599015712738},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0763842761516571},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07547077536582947},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.07437711954116821},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.0721997618675232}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8635910749435425},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7021480798721313},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5483019948005676},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5092185735702515},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5067635178565979},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.482713907957077},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.47140100598335266},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4543541669845581},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3406044840812683},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3125467896461487},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0774599015712738},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0763842761516571},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07547077536582947},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.07437711954116821},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0721997618675232},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11042-020-09783-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-020-09783-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-020-09783-9.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},{"id":"pmh:oai:zenodo.org:5730306","is_oa":true,"landing_page_url":"https://zenodo.org/record/5730306","pdf_url":"https://zenodo.org/record/5730306","source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s11042-020-09783-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-020-09783-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-020-09783-9.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3104339133","display_name":null,"funder_award_id":"Hungary","funder_id":"https://openalex.org/F4320326762","funder_display_name":"Nemzeti Kutat\u00e1si Fejleszt\u00e9si \u00e9s Innov\u00e1ci\u00f3s Hivatal"},{"id":"https://openalex.org/G4140855681","display_name":null,"funder_award_id":"825619","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5036817778","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innov","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8633428685","display_name":null,"funder_award_id":"European Union's Horizon 2020 research and innovat","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320311358","display_name":"Budapesti M\u0171szaki \u00e9s Gazdas\u00e1gtudom\u00e1nyi Egyetem","ror":"https://ror.org/02w42ss30"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320326762","display_name":"Nemzeti Kutat\u00e1si Fejleszt\u00e9si \u00e9s Innov\u00e1ci\u00f3s Hivatal","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3086073551.pdf","grobid_xml":"https://content.openalex.org/works/W3086073551.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W1499332833","https://openalex.org/W1509691205","https://openalex.org/W1512429158","https://openalex.org/W1546892833","https://openalex.org/W1570910243","https://openalex.org/W1980988001","https://openalex.org/W1990505856","https://openalex.org/W1998648683","https://openalex.org/W2004299580","https://openalex.org/W2012086895","https://openalex.org/W2021914964","https://openalex.org/W2022125261","https://openalex.org/W2029434926","https://openalex.org/W2037122044","https://openalex.org/W2049686551","https://openalex.org/W2056852181","https://openalex.org/W2064675550","https://openalex.org/W2066999516","https://openalex.org/W2091743772","https://openalex.org/W2092233629","https://openalex.org/W2102003408","https://openalex.org/W2107878631","https://openalex.org/W2108662299","https://openalex.org/W2114352222","https://openalex.org/W2118023920","https://openalex.org/W2120605154","https://openalex.org/W2126143605","https://openalex.org/W2127520494","https://openalex.org/W2128160875","https://openalex.org/W2129082420","https://openalex.org/W2129142580","https://openalex.org/W2130840866","https://openalex.org/W2131774270","https://openalex.org/W2142487393","https://openalex.org/W2145892079","https://openalex.org/W2152483743","https://openalex.org/W2154291215","https://openalex.org/W2155368638","https://openalex.org/W2156142001","https://openalex.org/W2287620236","https://openalex.org/W2287690143","https://openalex.org/W2294351487","https://openalex.org/W2294797155","https://openalex.org/W2296650368","https://openalex.org/W2296704011","https://openalex.org/W2343253662","https://openalex.org/W2471520273","https://openalex.org/W2524251915","https://openalex.org/W2598638573","https://openalex.org/W2742399401","https://openalex.org/W2746648261","https://openalex.org/W2747744257","https://openalex.org/W2749609415","https://openalex.org/W2785765285","https://openalex.org/W2790047899","https://openalex.org/W2800289214","https://openalex.org/W2801348287","https://openalex.org/W2804998325","https://openalex.org/W2915722758","https://openalex.org/W3100650420","https://openalex.org/W3177989406","https://openalex.org/W4206628346","https://openalex.org/W4239339398"],"related_works":["https://openalex.org/W1974895211","https://openalex.org/W2129841057","https://openalex.org/W3040712279","https://openalex.org/W2176409448","https://openalex.org/W2364769705","https://openalex.org/W2056136368","https://openalex.org/W2374664672","https://openalex.org/W4367555392","https://openalex.org/W2538520412","https://openalex.org/W2883092465"],"abstract_inverted_index":{"Abstract":[0],"This":[1],"article":[2],"focuses":[3],"on":[4],"developing":[5],"a":[6,36,45,80,95,111,119],"system":[7,115],"for":[8,40],"high-quality":[9],"synthesized":[10],"and":[11,60,66,97,107,139,155],"converted":[12],"speech":[13,93],"by":[14],"addressing":[15],"three":[16],"fundamental":[17,121],"principles.":[18],"Although":[19],"the":[20,24,69,147,151,160],"noise-like":[21],"component":[22],"in":[23,73,134],"state-of-the-art":[25],"parametric":[26],"vocoders":[27],"(for":[28],"example,":[29],"STRAIGHT)":[30],"is":[31,48,116],"often":[32],"not":[33],"accurate":[34,125],"enough,":[35],"novel":[37],"analytical":[38],"approach":[39],"modeling":[41],"unvoiced":[42],"excitations":[43],"using":[44,118],"temporal":[46],"envelope":[47],"proposed.":[49],"Discrete":[50],"All":[51],"Pole,":[52],"Frequency":[53],"Domain":[54],"Linear":[55],"Prediction,":[56],"Low":[57],"Pass":[58],"Filter,":[59],"True":[61],"envelopes":[62],"are":[63],"firstly":[64],"studied":[65],"applied":[67],"to":[68,123],"noise":[70],"excitation":[71],"signal":[72],"our":[74],"continuous":[75,120],"vocoder.":[76],"Second,":[77],"we":[78],"build":[79],"deep":[81],"learning":[82],"model":[83],"based":[84],"text\u2013to\u2013speech":[85],"(TTS)":[86],"which":[87],"converts":[88],"written":[89],"text":[90],"into":[91],"human-like":[92],"with":[94,159],"feed-forward":[96],"several":[98],"sequence-to-sequence":[99],"models":[100,149],"(long":[101],"short-term":[102],"memory,":[103],"gated":[104],"recurrent":[105],"unit,":[106],"hybrid":[108],"model).":[109],"Third,":[110],"new":[112],"voice":[113],"conversion":[114],"proposed":[117,148],"frequency":[122],"provide":[124],"time-aligned":[126],"voiced":[127],"segments.":[128],"The":[129],"results":[130,144],"have":[131],"been":[132],"evaluated":[133],"terms":[135],"of":[136],"objective":[137],"measures":[138],"subjective":[140],"listening":[141],"tests.":[142],"Experimental":[143],"showed":[145],"that":[146],"achieved":[150],"highest":[152],"speaker":[153],"similarity":[154],"better":[156],"quality":[157],"compared":[158],"other":[161],"conventional":[162],"methods.":[163]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}