{"id":"https://openalex.org/W4388820313","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317261","title":"Increasing Speech Intelligibility by Mimicking Professional Announcers\u2019 Voices and Its Physical Correlates","display_name":"Increasing Speech Intelligibility by Mimicking Professional Announcers\u2019 Voices and Its Physical Correlates","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388820313","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317261"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317261","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5101507065","display_name":"Dung Tran","orcid":null},"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":true,"raw_author_name":"Dung Kim Tran","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology,School of Information Science,Nomi,Japan,923-1292"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology,School of Information Science,Nomi,Japan,923-1292","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","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":["Japan Advanced Institute of Science and Technology,School of Information Science,Nomi,Japan,923-1292"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology,School of Information Science,Nomi,Japan,923-1292","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014199725","display_name":"Masashi Unoki","orcid":"https://orcid.org/0000-0002-6605-2052"},"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":"Masashi Unoki","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology,School of Information Science,Nomi,Japan,923-1292"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology,School of Information Science,Nomi,Japan,923-1292","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101507065"],"corresponding_institution_ids":["https://openalex.org/I177738480"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20229873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"119","issue":null,"first_page":"1187","last_page":"1192"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9951000213623047,"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":0.6334826350212097},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5122005343437195},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4945671260356903}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6334826350212097},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5122005343437195},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4945671260356903},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317261","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.jaist.ac.jp:10119/18769","is_oa":false,"landing_page_url":"http://hdl.handle.net/10119/18769","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":[],"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/W1881794303","https://openalex.org/W1971733741","https://openalex.org/W2013374607","https://openalex.org/W2022939667","https://openalex.org/W2029308246","https://openalex.org/W2035454529","https://openalex.org/W2043661469","https://openalex.org/W2066754815","https://openalex.org/W2068236232","https://openalex.org/W2084636655","https://openalex.org/W2085464700","https://openalex.org/W2293006933","https://openalex.org/W2399475675","https://openalex.org/W2404548911","https://openalex.org/W2405432219","https://openalex.org/W3015338123","https://openalex.org/W3096795913","https://openalex.org/W3196667132","https://openalex.org/W3202312061","https://openalex.org/W4283712502"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2127461790","https://openalex.org/W2069324367"],"abstract_inverted_index":{"Previous":[0],"studies":[1],"found":[2,153],"that":[3,13,54,141,154],"speech":[4,85,136],"uttered":[5],"by":[6,14,36,79,92],"professional":[7,33],"announcers":[8],"is":[9,120],"more":[10],"intelligible":[11],"than":[12],"non-experts":[15],"in":[16],"noisy":[17],"environments.":[18],"On":[19],"the":[20,38,71,73,101,105,117,124,135,145],"basis":[21],"of":[22,41,100,104,131,147,150],"this":[23,51,59,62,81],"finding,":[24],"we":[25,122,152],"developed":[26],"a":[27,128],"voice-conversion":[28],"(VC)":[29],"system":[30,52,108,126],"to":[31,49,64,70],"mimic":[32],"announcers\u2019":[34],"voices":[35],"modifying":[37],"speaker":[39,102],"embedding":[40,103],"non-expert":[42],"speech.":[43],"The":[44],"results":[45],"from":[46],"our":[47],"experiments":[48],"evaluate":[50],"indicated":[53],"intelligibility":[55,86,137],"increased":[56],"significantly":[57],"with":[58,127,144,166],"system.":[60],"In":[61],"paper,":[63],"discuss":[65],"what":[66,111],"physical":[67,112],"features":[68,113,140],"correlate":[69],"intelligibility,":[72],"following":[74],"two":[75],"issues":[76],"are":[77,114,163],"investigated":[78],"analyzing":[80],"system:":[82],"(1)":[83],"whether":[84],"can":[87],"be":[88],"changed":[89,115,143],"gradually":[90],"even":[91],"shifting":[93],"one":[94,148],"PCA":[95,118],"(principal":[96],"component":[97,99,119],"analysis)":[98],"above":[106],"VC":[107,125],"and":[109,138,159],"(2)":[110],"when":[116],"shifted,":[121],"retrained":[123],"larger":[129],"amount":[130],"training":[132],"data.":[133],"Comparing":[134],"candidate":[139],"were":[142],"shift":[146],"axis":[149],"PCA,":[151],"spectral":[155,157],"tilt,":[156],"plateau,":[158],"cepstral":[160],"peak":[161],"prominence":[162],"strongly":[164],"correlated":[165],"intelligibility.":[167]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}