{"id":"https://openalex.org/W4406858550","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848694","title":"A Pilot Study of Applying Sequence-to-Sequence Voice Conversion to Evaluate the Intelligibility of L2 Speech Using a Native Speaker\u2019s Shadowings","display_name":"A Pilot Study of Applying Sequence-to-Sequence Voice Conversion to Evaluate the Intelligibility of L2 Speech Using a Native Speaker\u2019s Shadowings","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406858550","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848694"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848694","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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":null,"display_name":"Haopeng Geng","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Haopeng Geng","raw_affiliation_strings":["The University of Tokyo,Graduate School of Engineering"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Graduate School of Engineering","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001092695","display_name":"Daisuke Saito","orcid":"https://orcid.org/0000-0003-4263-5453"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Saito","raw_affiliation_strings":["The University of Tokyo,Graduate School of Engineering"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Graduate School of Engineering","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":["The University of Tokyo,Graduate School of Engineering"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Graduate School of Engineering","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23587928,"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":0.7943000197410583,"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":0.7943000197410583,"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/speech-recognition","display_name":"Speech recognition","score":0.7071543335914612},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6659254431724548},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6102575063705444},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5841727256774902},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4123117923736572}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7071543335914612},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6659254431724548},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6102575063705444},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5841727256774902},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4123117923736572},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10848694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848694","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2141720691","https://openalex.org/W2168473804","https://openalex.org/W2745877834","https://openalex.org/W2888973864","https://openalex.org/W2890402938","https://openalex.org/W3011496487","https://openalex.org/W3015338123","https://openalex.org/W3015747801","https://openalex.org/W3083423753","https://openalex.org/W3096567388","https://openalex.org/W3096875076","https://openalex.org/W3118753411","https://openalex.org/W3162517041","https://openalex.org/W3163573274","https://openalex.org/W3170751106","https://openalex.org/W3178546316","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4210506357","https://openalex.org/W4236001005","https://openalex.org/W4287889585","https://openalex.org/W4297841366","https://openalex.org/W4385245566","https://openalex.org/W4385822605","https://openalex.org/W4388821525","https://openalex.org/W4389524060","https://openalex.org/W6712500554","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6800393981","https://openalex.org/W6847363464","https://openalex.org/W6854445763","https://openalex.org/W6854765073","https://openalex.org/W6867564123"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2081919107","https://openalex.org/W2127461790","https://openalex.org/W2069324367","https://openalex.org/W1540615732","https://openalex.org/W3115948027","https://openalex.org/W2405110677","https://openalex.org/W2811496854"],"abstract_inverted_index":{"Utterances":[0],"by":[1,56],"L2":[2,35,52,105],"speakers":[3,36,85],"can":[4],"be":[5,38],"unintelligible":[6,49],"due":[7],"to":[8,45,111,142],"mispronunciation":[9],"and":[10,47,87,151],"improper":[11],"prosody.":[12],"In":[13],"computer-aided":[14],"language":[15,57],"learning":[16],"systems,":[17],"textual":[18],"feedback":[19,33],"is":[20],"often":[21],"provided":[22],"using":[23,107],"a":[24,64,71,113,139],"speech":[25,106],"recognition":[26],"engine.":[27],"However,":[28],"an":[29,101],"ideal":[30],"form":[31],"of":[32,51,76,83,96,100,122,133],"for":[34],"should":[37],"so":[39],"fine-grained":[40],"that":[41],"it":[42],"enables":[43],"them":[44],"detect":[46],"diagnose":[48],"parts":[50],"speakers\u2019":[53,78],"utterances.":[54,90],"Inspired":[55],"teachers":[58],"who":[59],"correct":[60],"students\u2019":[61],"pronunciation":[62],"through":[63],"voice-to-voice":[65],"process,":[66],"this":[67],"pilot":[68],"study":[69],"utilizes":[70],"unique":[72],"semi-parallel":[73],"dataset":[74],"composed":[75],"non-native":[77],"(L2)":[79],"reading":[80],"aloud,":[81],"shadowing":[82,104,129,146],"native":[84],"(L1)":[86],"their":[88],"script-shadowing":[89],"We":[91],"explore":[92],"the":[93,98,120,123,134,143],"technical":[94],"possibility":[95],"replicating":[97],"process":[99],"L1":[102,145],"speaker\u2019s":[103],"Voice":[108],"Conversion":[109],"techniques,":[110],"create":[112],"virtual":[114,135],"shadower":[115,136],"system.":[116],"Experimental":[117],"results":[118],"demonstrate":[119],"feasibility":[121],"VC":[124],"system":[125,137],"in":[126,148],"simulating":[127],"L1\u2019s":[128],"behavior.":[130],"The":[131],"output":[132],"shows":[138],"reasonable":[140],"similarity":[141],"real":[144],"utterances":[147],"both":[149],"linguistic":[150],"acoustic":[152],"aspects<sup":[153],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[154],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[155]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}