{"id":"https://openalex.org/W4406859931","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848685","title":"Generation of target speech with speaker individuality based on accent conversion for English pronunciation learning","display_name":"Generation of target speech with speaker individuality based on accent conversion for English pronunciation learning","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406859931","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848685"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848685","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848685","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://kyutech.repo.nii.ac.jp/record/2001583/files/10450313.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055310076","display_name":"Rei Hamakawa","orcid":null},"institutions":[{"id":"https://openalex.org/I207014233","display_name":"Kyushu Institute of Technology","ror":"https://ror.org/02278tr80","country_code":"JP","type":"education","lineage":["https://openalex.org/I207014233"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rei Hamakawa","raw_affiliation_strings":["Kyushu Institute of Technology,Graduate School of Computer Science and Systems Engineering,Iizuka,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyushu Institute of Technology,Graduate School of Computer Science and Systems Engineering,Iizuka,Japan","institution_ids":["https://openalex.org/I207014233"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016859525","display_name":"Michiharu Niimi","orcid":null},"institutions":[{"id":"https://openalex.org/I207014233","display_name":"Kyushu Institute of Technology","ror":"https://ror.org/02278tr80","country_code":"JP","type":"education","lineage":["https://openalex.org/I207014233"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Michiharu Niimi","raw_affiliation_strings":["Kyushu Institute of Technology,Faculty of Computer Science and Systems Engineering,Iizuka,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyushu Institute of Technology,Faculty of Computer Science and Systems Engineering,Iizuka,Japan","institution_ids":["https://openalex.org/I207014233"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I207014233"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29374627,"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/T12031","display_name":"Speech and dialogue systems","score":0.7350000143051147,"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/T12031","display_name":"Speech and dialogue systems","score":0.7350000143051147,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.6710000038146973,"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/T14450","display_name":"Employee Welfare and Language Studies","score":0.63919997215271,"subfield":{"id":"https://openalex.org/subfields/1407","display_name":"Organizational Behavior and Human Resource Management"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.9163408279418945},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.8149877190589905},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7323645353317261},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6597539782524109},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4518061876296997},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41800373792648315},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41417396068573},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.40643927454948425}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.9163408279418945},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.8149877190589905},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7323645353317261},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6597539782524109},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4518061876296997},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41800373792648315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41417396068573},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.40643927454948425},{"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/apsipaasc63619.2025.10848685","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848685","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"},{"id":"pmh:oai:kyutech.repo.nii.ac.jp:02001583","is_oa":true,"landing_page_url":"https://kyutech.repo.nii.ac.jp/records/2001583","pdf_url":"https://kyutech.repo.nii.ac.jp/record/2001583/files/10450313.pdf","source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"AM"}],"best_oa_location":{"id":"pmh:oai:kyutech.repo.nii.ac.jp:02001583","is_oa":true,"landing_page_url":"https://kyutech.repo.nii.ac.jp/records/2001583","pdf_url":"https://kyutech.repo.nii.ac.jp/record/2001583/files/10450313.pdf","source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"AM"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406859931.pdf"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W93060608","https://openalex.org/W1494198834","https://openalex.org/W2017742648","https://openalex.org/W2888954148","https://openalex.org/W2964243274","https://openalex.org/W2983786745","https://openalex.org/W4297841851","https://openalex.org/W6603838645","https://openalex.org/W6631362777"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W4220683390","https://openalex.org/W117063597","https://openalex.org/W4289544804","https://openalex.org/W3031252497"],"abstract_inverted_index":{"This":[0],"paper":[1],"first":[2],"provides":[3],"an":[4],"overview":[5],"of":[6,73,81,93,104],"the":[7,22,27,47,63,68,79,82,91,98,102],"English":[8],"pronunciation":[9,71],"learning":[10],"support":[11],"tool.":[12],"The":[13,76],"tool":[14],"aims":[15],"to":[16,66,100],"use":[17],"\"accent-modified":[18],"speech":[19,95],"that":[20],"retains":[21],"learner\u2019s":[23],"voice":[24],"quality\"":[25],"as":[26,90],"\"target":[28],"speech.\"":[29],"We":[30],"propose":[31],"a":[32,57],"new":[33],"conversion":[34,54,84],"model":[35,51],"based":[36],"on":[37],"conventional":[38,48],"methods":[39],"for":[40,52],"this":[41],"accent":[42,53],"conversion.":[43],"Specifically,":[44],"we":[45],"improve":[46,101],"LSTM-based":[49],"DNN":[50],"by":[55],"adopting":[56],"transformer-based":[58],"model.":[59],"Our":[60],"experiments":[61],"investigated":[62],"model\u2019s":[64],"ability":[65],"handle":[67],"unique":[69],"katakana":[70],"characteristic":[72],"Japanese":[74,94],"speakers.":[75],"results":[77],"confirmed":[78],"effectiveness":[80],"proposed":[83],"method,":[85],"although":[86],"challenges":[87],"remain,":[88],"such":[89],"scarcity":[92],"data":[96],"and":[97],"need":[99],"accuracy":[103],"speaker":[105],"identity":[106],"retention.":[107]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}