{"id":"https://openalex.org/W2990640399","doi":"https://doi.org/10.1109/sped.2019.8906280","title":"WaveTract: A hybrid generative model for speech synthesis","display_name":"WaveTract: A hybrid generative model for speech synthesis","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2990640399","doi":"https://doi.org/10.1109/sped.2019.8906280","mag":"2990640399"},"language":"en","primary_location":{"id":"doi:10.1109/sped.2019.8906280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped.2019.8906280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","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/A5072606911","display_name":"Brun\u00f3 B. Englert","orcid":null},"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":"Brun\u00f3 Bence Englert","raw_affiliation_strings":["Budapest University of Technology and Economics,Department of Telecommunications and Media Informatics,Budapest,Hungary","Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics,Department of Telecommunications and Media Informatics,Budapest,Hungary","institution_ids":["https://openalex.org/I29770179"]},{"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/A5031237235","display_name":"Csaba Zaink\u00f3","orcid":null},"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":"Csaba Zaink\u00f3","raw_affiliation_strings":["Budapest University of Technology and Economics,Department of Telecommunications and Media Informatics,Budapest,Hungary","Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics,Department of Telecommunications and Media Informatics,Budapest,Hungary","institution_ids":["https://openalex.org/I29770179"]},{"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":"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":["Budapest University of Technology and Economics,Department of Telecommunications and Media Informatics,Budapest,Hungary","Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics,Department of Telecommunications and Media Informatics,Budapest,Hungary","institution_ids":["https://openalex.org/I29770179"]},{"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":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15059535,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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":0.9995999932289124,"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/upsampling","display_name":"Upsampling","score":0.8780652284622192},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8370612859725952},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6583512425422668},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6331006288528442},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5764879584312439},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5351622700691223},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.49344030022621155},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.45683759450912476},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44430598616600037},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.44229912757873535},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3097723722457886},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.30825918912887573}],"concepts":[{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.8780652284622192},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8370612859725952},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6583512425422668},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6331006288528442},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5764879584312439},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5351622700691223},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.49344030022621155},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.45683759450912476},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44430598616600037},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44229912757873535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3097723722457886},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.30825918912887573},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sped.2019.8906280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped.2019.8906280","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","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":14,"referenced_works":["https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2584505851","https://openalex.org/W2769810959","https://openalex.org/W2819579046","https://openalex.org/W2963139417","https://openalex.org/W2963300588","https://openalex.org/W2963782041","https://openalex.org/W2964243274","https://openalex.org/W4289761690","https://openalex.org/W4294619240","https://openalex.org/W6746700228","https://openalex.org/W6755592152","https://openalex.org/W7042468797"],"related_works":["https://openalex.org/W2062399876","https://openalex.org/W2607795551","https://openalex.org/W2079194684","https://openalex.org/W3155117723","https://openalex.org/W1991429770","https://openalex.org/W2020989338","https://openalex.org/W1823617068","https://openalex.org/W2147126679","https://openalex.org/W4300049944","https://openalex.org/W2115039802"],"abstract_inverted_index":{"In":[0],"this":[1,60],"paper":[2],"we":[3],"propose":[4],"a":[5,11,31,39,78,84,109],"hybrid":[6,45],"speech":[7,27],"synthesizer,":[8],"which":[9],"combines":[10],"neural":[12,53],"network":[13],"based":[14],"synthesizer":[15],"with":[16,30],"an":[17],"acoustical":[18],"vocal":[19,41,67],"tract":[20,68],"model.":[21],"Low":[22],"frequency":[23],"audio":[24,34,76,86],"of":[25],"the":[26,56,66,97,114,127],"is":[28,35,63],"generated":[29],"WaveGlow.":[32],"This":[33,125],"then":[36],"upsampled":[37],"by":[38],"simulated":[40],"tract.":[42],"The":[43,88,102],"proposed":[44,61,89],"model":[46,62,69,90],"can":[47,70,105],"be":[48,71,106,135],"trained":[49],"as":[50],"any":[51],"supervised":[52],"network.":[54],"Since":[55],"WaveGlow":[57],"used":[58],"in":[59],"smaller":[64],"and":[65,82],"implemented":[72],"efficiently,":[73],"it":[74,93],"produces":[75],"at":[77,113,130],"much":[79],"higher":[80],"speed":[81],"delivers":[83],"decent":[85],"quality.":[87],"also":[91,134],"makes":[92],"possible":[94],"to":[95],"divide":[96],"inference":[98],"into":[99],"two":[100],"parts.":[101],"upsampling":[103],"process":[104],"done":[107],"on":[108],"low":[110],"performance":[111,129],"CPU":[112],"client":[115],"side,":[116],"for":[117],"example":[118],"mobile":[119],"phones":[120],"or":[121],"home":[122],"assistant":[123],"devices.":[124],"way":[126],"required":[128],"server":[131],"side":[132],"will":[133],"lower.":[136]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}