{"id":"https://openalex.org/W4283712502","doi":"https://doi.org/10.21437/interspeech.2022-124","title":"Speak Like a Professional: Increasing Speech Intelligibility by Mimicking Professional Announcer Voice with Voice Conversion","display_name":"Speak Like a Professional: Increasing Speech Intelligibility by Mimicking Professional Announcer Voice with Voice Conversion","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283712502","doi":"https://doi.org/10.21437/interspeech.2022-124"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-124","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-124","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5083304186","display_name":"Tuan Vu Ho","orcid":"https://orcid.org/0000-0001-6819-0443"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tuan Vu Ho","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101054645","display_name":"Maori Kobayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Maori Kobayashi","raw_affiliation_strings":["School of Human Sciences,Waseda University"],"affiliations":[{"raw_affiliation_string":"School of Human Sciences,Waseda University","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055059119","display_name":"Masato Akagi","orcid":"https://orcid.org/0000-0003-2450-6754"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Akagi","raw_affiliation_strings":["School of Information Science, Japan Advanced Institute of Science and Technology"],"affiliations":[{"raw_affiliation_string":"School of Information Science, Japan Advanced Institute of Science and Technology","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5083304186"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1215,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.22222222,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"171","last_page":"175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9128000140190125,"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":0.9128000140190125,"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":0.9003000259399414,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.8662065267562866},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.706214189529419},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6739909648895264},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6272778511047363},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.44759753346443176},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.27726826071739197},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.15704691410064697},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12462005019187927}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.8662065267562866},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.706214189529419},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6739909648895264},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6272778511047363},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.44759753346443176},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27726826071739197},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.15704691410064697},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12462005019187927},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":2,"locations":[{"id":"doi:10.21437/interspeech.2022-124","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-124","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.jaist.ac.jp:10119/18156","is_oa":false,"landing_page_url":"http://hdl.handle.net/10119/18156","pdf_url":null,"source":{"id":"https://openalex.org/S4406922663","display_name":"JAIST Repository","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G190845862","display_name":null,"funder_award_id":"201605002","funder_id":"https://openalex.org/F4320325628","funder_display_name":"Ministry of Internal Affairs and Communications"},{"id":"https://openalex.org/G2732612706","display_name":null,"funder_award_id":"SCOPE","funder_id":"https://openalex.org/F4320325628","funder_display_name":"Ministry of Internal Affairs and Communications"}],"funders":[{"id":"https://openalex.org/F4320325628","display_name":"Ministry of Internal Affairs and Communications","ror":"https://ror.org/00vs1pz50"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1875231349","https://openalex.org/W1881794303","https://openalex.org/W1971733741","https://openalex.org/W1997307245","https://openalex.org/W2043661469","https://openalex.org/W2066754815","https://openalex.org/W2067295501","https://openalex.org/W2084636655","https://openalex.org/W2194775991","https://openalex.org/W2293006933","https://openalex.org/W2399475675","https://openalex.org/W2404548911","https://openalex.org/W2405432219","https://openalex.org/W2962780374","https://openalex.org/W3011028252","https://openalex.org/W3015338123","https://openalex.org/W3034600949","https://openalex.org/W3096795913","https://openalex.org/W3196667132","https://openalex.org/W3202312061"],"related_works":["https://openalex.org/W2085637247","https://openalex.org/W2127461790","https://openalex.org/W2069324367","https://openalex.org/W3042618827","https://openalex.org/W2231565466","https://openalex.org/W2964951088","https://openalex.org/W197907117","https://openalex.org/W2978471304","https://openalex.org/W2280467666","https://openalex.org/W2621540445"],"abstract_inverted_index":{"In":[0],"most":[1],"of":[2,35,42,51,61,81,145,152,173,182,189],"practical":[3],"scenarios,":[4],"the":[5,18,36,40,71,78,116,128,135,150,179],"announcement":[6,43],"system":[7],"must":[8],"deliver":[9],"speech":[10,29,72,99,136,180],"messages":[11],"in":[12,16,64,102,155,164,192],"a":[13,98],"noisy":[14,65,103,156],"environment,":[15,157],"which":[17,84],"background":[19],"noise":[20,27,166],"cannot":[21],"be":[22,75,86,139],"cancelled":[23],"out.":[24],"The":[25,171],"local":[26],"reduces":[28],"intelligibility":[30,73,100,137,181],"and":[31,56,119],"increases":[32],"listening":[33],"effort":[34],"listener,":[37],"hence":[38],"hamper":[39],"effectiveness":[41],"system.":[44],"There":[45],"has":[46],"been":[47],"reported":[48],"that":[49,60,70,115,134,178,188],"voices":[50],"professional":[52,82,117],"announcers":[53,118],"are":[54,122],"clearer":[55],"more":[57],"comprehensive":[58],"than":[59,187],"nonexpert":[62],"speakers":[63,121],"environment.":[66],"This":[67,132],"finding":[68],"suggests":[69],"might":[74],"related":[76],"to":[77],"speaking":[79],"style":[80],"announcer,":[83],"can":[85,138],"adapted":[87],"using\\nvoice":[88],"conversion":[89,108],"method.":[90],"Motivated":[91],"by":[92,105],"this":[93,95],"idea,":[94],"paper":[96],"proposes":[97],"enhancement":[101],"environment":[104],"applying":[106],"voice":[107,154,184,191],"method":[109],"on":[110,127],"non-professional":[111],"voice.":[112],"We":[113],"discovered":[114],"nonprofessional":[120],"clusterized":[123],"into":[124],"different":[125,168],"clusters":[126],"speaker":[129,146],"embedding":[130],"plane.":[131],"implies":[133],"controlled":[140],"as":[141],"an":[142],"independent":[143],"feature":[144],"individuality.":[147],"To":[148],"examine":[149],"advantage":[151],"converted":[153,183],"we":[158],"experimented":[159],"using":[160],"test":[161],"words":[162],"masked":[163],"pink":[165],"at":[167],"SNR":[169,194],"levels.":[170],"results":[172],"objective\\nand":[174],"subjective":[175],"evaluations":[176],"confirm":[177],"is":[185],"higher":[186],"original":[190],"low":[193],"conditions.":[195]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
