{"id":"https://openalex.org/W4318752101","doi":"https://doi.org/10.1109/slt54892.2023.10022796","title":"Generative Models for Improved Naturalness, Intelligibility, and Voicing of Whispered Speech","display_name":"Generative Models for Improved Naturalness, Intelligibility, and Voicing of Whispered Speech","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4318752101","doi":"https://doi.org/10.1109/slt54892.2023.10022796"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022796","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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 IEEE Spoken Language Technology Workshop (SLT)","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/A5016617263","display_name":"Dominik Wagner","orcid":"https://orcid.org/0000-0002-3631-4138"},"institutions":[{"id":"https://openalex.org/I4210100612","display_name":"Georg Simon Ohm University of Applied Sciences Nuremberg","ror":"https://ror.org/00nggaz43","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210100612"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dominik Wagner","raw_affiliation_strings":["Technische Hochschule Nürnberg Georg Simon Ohm,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Hochschule Nürnberg Georg Simon Ohm,Germany","institution_ids":["https://openalex.org/I4210100612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070508803","display_name":"Sebastian P. Bayerl","orcid":"https://orcid.org/0000-0002-3502-9511"},"institutions":[{"id":"https://openalex.org/I4210100612","display_name":"Georg Simon Ohm University of Applied Sciences Nuremberg","ror":"https://ror.org/00nggaz43","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210100612"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian P. Bayerl","raw_affiliation_strings":["Technische Hochschule Nürnberg Georg Simon Ohm,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Hochschule Nürnberg Georg Simon Ohm,Germany","institution_ids":["https://openalex.org/I4210100612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080681245","display_name":"Hector A. Cordourier Maruri","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hector A. Cordourier Maruri","raw_affiliation_strings":["Intel Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033302750","display_name":"Tobias Bocklet","orcid":"https://orcid.org/0009-0008-7780-8821"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I4210100612","display_name":"Georg Simon Ohm University of Applied Sciences Nuremberg","ror":"https://ror.org/00nggaz43","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210100612"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Tobias Bocklet","raw_affiliation_strings":["Technische Hochschule Nürnberg Georg Simon Ohm,Germany","Intel Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Hochschule Nürnberg Georg Simon Ohm,Germany","institution_ids":["https://openalex.org/I4210100612"]},{"raw_affiliation_string":"Intel Labs","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.45,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.83622306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"943","last_page":"948"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9934999942779541,"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/naturalness","display_name":"Naturalness","score":0.9421862363815308},{"id":"https://openalex.org/keywords/voice","display_name":"Voice","score":0.897365152835846},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7572996616363525},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6461734771728516},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.640661358833313},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3285500407218933},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12317964434623718}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9421862363815308},{"id":"https://openalex.org/C552089266","wikidata":"https://www.wikidata.org/wiki/Q494510","display_name":"Voice","level":2,"score":0.897365152835846},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7572996616363525},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6461734771728516},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.640661358833313},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3285500407218933},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12317964434623718},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/slt54892.2023.10022796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022796","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:kobv.de-opus4-th-nuernberg:1613","is_oa":false,"landing_page_url":"https://opus4.kobv.de/opus4-ohm/frontdoor/index/index/docId/1613","pdf_url":null,"source":{"id":"https://openalex.org/S4306401730","display_name":"OHMdok (Technische Hochschule N\u00fcrnberg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210100612","host_organization_name":"Georg Simon Ohm University of Applied Sciences Nuremberg","host_organization_lineage":["https://openalex.org/I4210100612"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceobject"},{"id":"pmh:oai:kobv.de-opus4-th-nuernberg:1763","is_oa":false,"landing_page_url":"https://opus4.kobv.de/opus4-ohm/frontdoor/index/index/docId/1763","pdf_url":null,"source":{"id":"https://openalex.org/S4306401730","display_name":"OHMdok (Technische Hochschule N\u00fcrnberg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210100612","host_organization_name":"Georg Simon Ohm University of Applied Sciences Nuremberg","host_organization_lineage":["https://openalex.org/I4210100612"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceobject"},{"id":"pmh:oai:kobv.de-opus4-th-nuernberg:2162","is_oa":false,"landing_page_url":"https://opus4.kobv.de/opus4-ohm/frontdoor/index/index/docId/2162","pdf_url":null,"source":{"id":"https://openalex.org/S4306401730","display_name":"OHMdok (Technische Hochschule N\u00fcrnberg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210100612","host_organization_name":"Georg Simon Ohm University of Applied Sciences Nuremberg","host_organization_lineage":["https://openalex.org/I4210100612"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conferenceobject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4099999964237213,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W96541173","https://openalex.org/W1538607601","https://openalex.org/W1540787848","https://openalex.org/W1583837637","https://openalex.org/W1936400760","https://openalex.org/W1963637322","https://openalex.org/W2067295501","https://openalex.org/W2187089797","https://openalex.org/W2242818861","https://openalex.org/W2752796333","https://openalex.org/W2804145368","https://openalex.org/W2889417860","https://openalex.org/W2911495555","https://openalex.org/W2962793481","https://openalex.org/W2962795274","https://openalex.org/W2963300588","https://openalex.org/W2963341071","https://openalex.org/W2963799213","https://openalex.org/W2970006822","https://openalex.org/W2972471621","https://openalex.org/W2987496713","https://openalex.org/W3036601975","https://openalex.org/W3089425003","https://openalex.org/W3096359062","https://openalex.org/W3100270690","https://openalex.org/W3140957872","https://openalex.org/W3197642003","https://openalex.org/W3208900277","https://openalex.org/W4237182219","https://openalex.org/W4238582696","https://openalex.org/W4319750153","https://openalex.org/W6640963894","https://openalex.org/W6687506355","https://openalex.org/W6690026940","https://openalex.org/W6735204497","https://openalex.org/W6751821244","https://openalex.org/W6753018729","https://openalex.org/W6767111847","https://openalex.org/W6780218876","https://openalex.org/W6792367290","https://openalex.org/W6802929171","https://openalex.org/W6810426031"],"related_works":["https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W1604114751","https://openalex.org/W4252942110","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W2549308614","https://openalex.org/W3018584924","https://openalex.org/W2023694213","https://openalex.org/W2958354987"],"abstract_inverted_index":{"This":[0],"work":[1],"adapts":[2],"two":[3],"recent":[4],"architectures":[5],"of":[6,16,32],"generative":[7],"models":[8],"and":[9,37,51,59,104],"evaluates":[10],"their":[11],"effectiveness":[12],"for":[13],"the":[14,24,29,41,66,72,77,97,108,133],"conversion":[15,67],"whispered":[17,48,109],"speech":[18,27,46,121],"to":[19,43,64,88,107,132],"normal":[20,25],"speech.":[21,111],"We":[22,69],"incorporate":[23],"target":[26],"into":[28],"training":[30],"criterion":[31],"vector-quantized":[33],"variational":[34],"autoencoders":[35],"(VQ-VAEs)":[36],"Mel-GANs,":[38],"thereby":[39],"conditioning":[40],"systems":[42],"recover":[44],"voiced":[45],"from":[47],"inputs.":[49],"Objective":[50],"subjective":[52],"quality":[53],"measures":[54],"indicate":[55],"that":[56,71,96,125],"both":[57],"VQ-VAEs":[58],"MelGANs":[60],"can":[61],"be":[62],"modified":[63],"perform":[65],"task.":[68],"find":[70],"proposed":[73],"approaches":[74],"significantly":[75,100],"improve":[76],"Mel":[78],"cepstral":[79],"distortion":[80],"(MCD)":[81],"metric":[82],"by":[83],"at":[84],"least":[85],"25%":[86],"relative":[87,131],"a":[89],"Disco-GAN":[90],"baseline.":[91,134],"Subjective":[92],"listening":[93],"tests":[94],"suggest":[95],"MelGAN-based":[98,127],"system":[99],"improves":[101],"naturalness,":[102],"intelligibility,":[103],"voicing":[105],"compared":[106],"input":[110],"A":[112],"novel":[113],"evaluation":[114],"measure":[115],"based":[116],"on":[117],"differences":[118],"between":[119],"latent":[120],"representations":[122],"also":[123],"indicates":[124],"our":[126],"approach":[128],"yields":[129],"improvements":[130]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}