{"id":"https://openalex.org/W4406266905","doi":"https://doi.org/10.1109/gcce62371.2024.10760776","title":"Comparison of Large Pre-trained Models and Adaptation Methods for Japanese Dialects ASR","display_name":"Comparison of Large Pre-trained Models and Adaptation Methods for Japanese Dialects ASR","publication_year":2024,"publication_date":"2024-10-29","ids":{"openalex":"https://openalex.org/W4406266905","doi":"https://doi.org/10.1109/gcce62371.2024.10760776"},"language":"en","primary_location":{"id":"doi:10.1109/gcce62371.2024.10760776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce62371.2024.10760776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 13th Global Conference on Consumer Electronics (GCCE)","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/A5043935976","display_name":"Naoki Takahashi","orcid":"https://orcid.org/0000-0001-8952-7260"},"institutions":[{"id":"https://openalex.org/I1298590031","display_name":"Shizuoka University","ror":"https://ror.org/01w6wtk13","country_code":"JP","type":"education","lineage":["https://openalex.org/I1298590031"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Naoki Takahashi","raw_affiliation_strings":["Shizuoka University,Graduate School of Integrated Science and Technology,Shizuoka,Japan"],"affiliations":[{"raw_affiliation_string":"Shizuoka University,Graduate School of Integrated Science and Technology,Shizuoka,Japan","institution_ids":["https://openalex.org/I1298590031"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058845489","display_name":"Shogo Miwa","orcid":null},"institutions":[{"id":"https://openalex.org/I1298590031","display_name":"Shizuoka University","ror":"https://ror.org/01w6wtk13","country_code":"JP","type":"education","lineage":["https://openalex.org/I1298590031"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shogo Miwa","raw_affiliation_strings":["Shizuoka University,Graduate School of Integrated Science and Technology,Shizuoka,Japan"],"affiliations":[{"raw_affiliation_string":"Shizuoka University,Graduate School of Integrated Science and Technology,Shizuoka,Japan","institution_ids":["https://openalex.org/I1298590031"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007230879","display_name":"Yuta Kamiya","orcid":null},"institutions":[{"id":"https://openalex.org/I1298590031","display_name":"Shizuoka University","ror":"https://ror.org/01w6wtk13","country_code":"JP","type":"education","lineage":["https://openalex.org/I1298590031"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuta Kamiya","raw_affiliation_strings":["Shizuoka University,Graduate School of Integrated Science and Technology,Shizuoka,Japan"],"affiliations":[{"raw_affiliation_string":"Shizuoka University,Graduate School of Integrated Science and Technology,Shizuoka,Japan","institution_ids":["https://openalex.org/I1298590031"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005043937","display_name":"Takumi Toyama","orcid":null},"institutions":[{"id":"https://openalex.org/I1298590031","display_name":"Shizuoka University","ror":"https://ror.org/01w6wtk13","country_code":"JP","type":"education","lineage":["https://openalex.org/I1298590031"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takumi Toyama","raw_affiliation_strings":["Shizuoka University,Graduate School of Integrated Science and Technology,Shizuoka,Japan"],"affiliations":[{"raw_affiliation_string":"Shizuoka University,Graduate School of Integrated Science and Technology,Shizuoka,Japan","institution_ids":["https://openalex.org/I1298590031"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066860291","display_name":"Raufun Nahar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092186","display_name":"Anan National College of Technology","ror":"https://ror.org/01bb68v37","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210092186"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Raufun Nahar","raw_affiliation_strings":["Anan National College of Technology,Center for Education in Advanced Information Technology,Tokushima,Japan"],"affiliations":[{"raw_affiliation_string":"Anan National College of Technology,Center for Education in Advanced Information Technology,Tokushima,Japan","institution_ids":["https://openalex.org/I4210092186"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071123569","display_name":"Atsuhiko Kai","orcid":null},"institutions":[{"id":"https://openalex.org/I1298590031","display_name":"Shizuoka University","ror":"https://ror.org/01w6wtk13","country_code":"JP","type":"education","lineage":["https://openalex.org/I1298590031"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsuhiko Kai","raw_affiliation_strings":["Shizuoka University,Graduate School of Integrated Science and Technology,Shizuoka,Japan"],"affiliations":[{"raw_affiliation_string":"Shizuoka University,Graduate School of Integrated Science and Technology,Shizuoka,Japan","institution_ids":["https://openalex.org/I1298590031"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5043935976"],"corresponding_institution_ids":["https://openalex.org/I1298590031"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2341058,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"811","last_page":"814"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9830999970436096,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9830999970436096,"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":0.9713000059127808,"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/T10028","display_name":"Topic Modeling","score":0.9578999876976013,"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/adaptation","display_name":"Adaptation (eye)","score":0.7299343347549438},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7063249349594116},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4580906331539154},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4458513855934143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4167674481868744},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09799471497535706}],"concepts":[{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7299343347549438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7063249349594116},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4580906331539154},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4458513855934143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4167674481868744},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09799471497535706},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gcce62371.2024.10760776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce62371.2024.10760776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 13th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"the":[3,36,45,52],"accuracy":[4],"of":[5,41,44,54,79,83],"automatic":[6],"speech":[7],"recognition":[8],"(ASR)":[9],"for":[10,60,66,91,123],"major":[11],"languages":[12],"has":[13,29],"been":[14,32],"greatly":[15],"improved":[16],"by":[17],"pre-training":[18],"methods":[19,119],"using":[20,76],"large":[21,37,57],"spoken":[22],"language":[23],"resources.":[24],"However,":[25],"practical":[26],"ASR":[27,64,121],"technology":[28],"not":[30],"yet":[31],"realized":[33],"to":[34],"cover":[35],"and":[38],"rich":[39],"variety":[40],"regional":[42],"dialects":[43],"Japanese":[46,67,84,124],"language.":[47],"This":[48],"study":[49],"focuses":[50],"on":[51],"adaptability":[53],"two":[55,110],"state-of-the-art":[56],"pretrained":[58],"models":[59,75,89,100],"building":[61],"a":[62,77],"unified":[63],"model":[65],"dialects.":[68,125],"We":[69,87],"present":[70],"results":[71],"from":[72],"adapting":[73],"these":[74,109],"total":[78],"several":[80],"dozen":[81],"hours":[82],"dialect":[85,93,96,105],"speech.":[86],"compare":[88],"optimized":[90],"each":[92],"region,":[94],"including":[95],"region":[97],"identification,":[98],"with":[99],"adapted":[101],"without":[102],"distinguishing":[103],"between":[104],"regions.":[106],"By":[107],"comparing":[108],"different":[111],"learning":[112],"processes,":[113],"we":[114],"investigate":[115],"how":[116],"various":[117],"adaptation":[118],"impact":[120],"performance":[122]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}