{"id":"https://openalex.org/W4388821525","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317592","title":"Evaluating Methods for Ground-Truth-Free Foreign Accent Conversion","display_name":"Evaluating Methods for Ground-Truth-Free Foreign Accent Conversion","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388821525","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317592"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc58517.2023.10317592","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":"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/A5000377034","display_name":"Wen-Chin Huang","orcid":"https://orcid.org/0000-0003-3172-3335"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wen-Chin Huang","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1161","last_page":"1166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9972000122070312,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9969000220298767,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7500674724578857},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6508463621139526},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5876986384391785},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.552990734577179},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.493269145488739},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.49175480008125305},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4872407019138336},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35510173439979553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3100997805595398},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.12285348773002625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7500674724578857},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6508463621139526},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5876986384391785},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.552990734577179},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.493269145488739},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.49175480008125305},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4872407019138336},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35510173439979553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3100997805595398},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.12285348773002625},{"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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc58517.2023.10317592","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4399999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1556869580","https://openalex.org/W1892640180","https://openalex.org/W1991682319","https://openalex.org/W2017742648","https://openalex.org/W2020304287","https://openalex.org/W2022241205","https://openalex.org/W2023407680","https://openalex.org/W2023728986","https://openalex.org/W2168473804","https://openalex.org/W2249663999","https://openalex.org/W2518172956","https://openalex.org/W2576309025","https://openalex.org/W2888954148","https://openalex.org/W2890402938","https://openalex.org/W2946200149","https://openalex.org/W2964243274","https://openalex.org/W2973142754","https://openalex.org/W2979476256","https://openalex.org/W2983786745","https://openalex.org/W2995181338","https://openalex.org/W3015338123","https://openalex.org/W3015430779","https://openalex.org/W3036601975","https://openalex.org/W3082130377","https://openalex.org/W3083776549","https://openalex.org/W3096567388","https://openalex.org/W3098557217","https://openalex.org/W3118753411","https://openalex.org/W3162517041","https://openalex.org/W3178546316","https://openalex.org/W3198218550","https://openalex.org/W3207300132","https://openalex.org/W3207399576","https://openalex.org/W4287889585","https://openalex.org/W4296068974","https://openalex.org/W4297841851","https://openalex.org/W4385245566","https://openalex.org/W6633244395","https://openalex.org/W6691692526","https://openalex.org/W6739901393","https://openalex.org/W6763832098","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6840412704"],"related_works":["https://openalex.org/W4367680763","https://openalex.org/W2739335048","https://openalex.org/W1506224037","https://openalex.org/W4213177143","https://openalex.org/W2151922127","https://openalex.org/W4237818736","https://openalex.org/W4252005663","https://openalex.org/W2365914832","https://openalex.org/W2127461790","https://openalex.org/W2069324367"],"abstract_inverted_index":{"Foreign":[0],"accent":[1,87],"conversion":[2,10],"(FAC)":[3],"is":[4,33,51,113,170],"a":[5,20,24],"special":[6],"application":[7],"of":[8,19,69,76,127,136,145],"voice":[9],"(VC)":[11],"which":[12,112],"aims":[13],"to":[14,23,44,53,72,83,116,172],"convert":[15,85],"the":[16,28,36,40,48,74,86,90,106,125,131,137,142,146,182],"accented":[17],"speech":[18,26,38],"non-native":[21,42],"speaker":[22,30,43,91],"native-sounding":[25],"with":[27,130,164],"same":[29],"identity.":[31,92],"FAC":[32],"difficult":[34],"since":[35],"native":[37],"from":[39],"desired":[41],"be":[45],"used":[46],"as":[47,156],"training":[49,132],"target":[50],"impossible":[52],"collect.":[54],"In":[55],"this":[56],"work,":[57],"we":[58],"evaluate":[59],"three":[60],"recently":[61],"proposed":[62],"methods":[63,129],"for":[64],"ground-truth-free":[65],"FAC,":[66],"where":[67],"all":[68,109],"them":[70],"aim":[71],"harness":[73],"power":[75],"sequence-to-sequence":[77],"(seq2seq)":[78],"and":[79,88,134,140,150,176],"non-parallel":[80,147],"VC":[81,148],"models":[82],"properly":[84],"control":[89],"Our":[93],"experimental":[94],"evaluation":[95,110],"results":[96],"show":[97,151],"that":[98,152],"no":[99],"single":[100],"method":[101],"was":[102],"significantly":[103],"better":[104],"than":[105],"others":[107],"in":[108,114,119],"axes,":[111],"contrast":[115],"conclusions":[117],"drawn":[118],"previous":[120],"studies.":[121],"We":[122],"also":[123],"explain":[124],"effectiveness":[126],"these":[128],"input":[133],"output":[135],"seq2seq":[138],"model":[139],"examine":[141],"design":[143],"choice":[144],"model,":[149],"intelligibility":[153],"measures":[154],"such":[155],"word":[157],"error":[158],"rates":[159],"do":[160],"not":[161],"correlate":[162],"well":[163],"subjective":[165],"accentedness.":[166],"Finally,":[167],"our":[168],"implementation":[169],"open-sourced":[171],"promote":[173],"reproducible":[174],"research":[175],"help":[177],"future":[178],"researchers":[179],"improve":[180],"upon":[181],"compared":[183],"systems.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}