{"id":"https://openalex.org/W4405633822","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800608","title":"A Parameter-Efficient Multi-Step Fine-Tuning of Multilingual and Multi-Task Learning Model for Japanese Dialect Speech Recognition","display_name":"A Parameter-Efficient Multi-Step Fine-Tuning of Multilingual and Multi-Task Learning Model for Japanese Dialect Speech Recognition","publication_year":2024,"publication_date":"2024-10-17","ids":{"openalex":"https://openalex.org/W4405633822","doi":"https://doi.org/10.1109/o-cocosda64382.2024.10800608"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda64382.2024.10800608","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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/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":true,"raw_author_name":"Yuta Kamiya","raw_affiliation_strings":["Graduate School of Integrated Science and Technology, Shizuoka University,Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Integrated Science and Technology, Shizuoka University,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":["Graduate School of Integrated Science and Technology, Shizuoka University,Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Integrated Science and Technology, Shizuoka University,Japan","institution_ids":["https://openalex.org/I1298590031"]}]},{"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":["Graduate School of Integrated Science and Technology, Shizuoka University,Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Integrated Science and Technology, Shizuoka University,Japan","institution_ids":["https://openalex.org/I1298590031"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5007230879"],"corresponding_institution_ids":["https://openalex.org/I1298590031"],"apc_list":null,"apc_paid":null,"fwci":0.3626,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70104129,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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":0.9386000037193298,"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":0.9386000037193298,"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/computer-science","display_name":"Computer science","score":0.8285308480262756},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7159502506256104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6423036456108093},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49294185638427734},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4581630825996399},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4141339063644409},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06832128763198853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8285308480262756},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7159502506256104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6423036456108093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49294185638427734},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4581630825996399},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4141339063644409},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06832128763198853},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda64382.2024.10800608","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda64382.2024.10800608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2933138175","https://openalex.org/W2972389417","https://openalex.org/W2973049979","https://openalex.org/W3104215796","https://openalex.org/W3180180466","https://openalex.org/W3198429080","https://openalex.org/W3201225328","https://openalex.org/W3203633372","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3212799896","https://openalex.org/W3213029956","https://openalex.org/W4225096077","https://openalex.org/W4225274946","https://openalex.org/W4225739182","https://openalex.org/W4285144981","https://openalex.org/W4296070193","https://openalex.org/W4385822483","https://openalex.org/W4385823097","https://openalex.org/W6601563604","https://openalex.org/W6674330103","https://openalex.org/W6759579507","https://openalex.org/W6761472960","https://openalex.org/W6780218876","https://openalex.org/W6788335241","https://openalex.org/W6838701581"],"related_works":["https://openalex.org/W2803309984","https://openalex.org/W2963872552","https://openalex.org/W2237537322","https://openalex.org/W4301248618","https://openalex.org/W2950678851","https://openalex.org/W2914746235","https://openalex.org/W3188962172","https://openalex.org/W4389443772","https://openalex.org/W3204019825","https://openalex.org/W2951720331"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,17,31,45,73,119,127],"challenge":[4],"of":[5,20,33,44,75,109],"developing":[6],"a":[7,85,102],"unified":[8],"spoken":[9],"language":[10,41],"model":[11],"for":[12,131],"Japanese":[13,34,56],"dialects.":[14],"Due":[15],"to":[16,40,112],"limited":[18],"availability":[19],"such":[21],"speech":[22,57],"resources,":[23],"self-supervised":[24],"learning":[25,60],"(SSL)":[26],"methods":[27],"show":[28],"promise.":[29],"However,":[30,65],"diversity":[32],"dialects":[35],"also":[36],"requires":[37],"multilingual":[38,87],"approaches":[39],"modeling.":[42],"One":[43],"few":[46],"related":[47],"works":[48],"improved":[49],"performance":[50],"through":[51],"multi-step":[52],"fine-tuning,":[53],"using":[54,93,124],"standard":[55],"and":[58,71],"multitask":[59],"that":[61],"incorporates":[62],"dialect":[63],"identification.":[64],"this":[66],"method":[67,100],"is":[68],"computationally":[69],"expensive":[70],"runs":[72],"risk":[74],"forgetting":[76],"acquired":[77],"knowledge.":[78],"To":[79],"address":[80],"these":[81],"challenges,":[82],"we":[83],"propose":[84],"large-scale":[86],"SSL":[88],"model-based":[89],"multistage":[90],"fine-tuning":[91,115],"strategy":[92],"lightweight":[94],"adapter":[95],"modules":[96],"per":[97],"domain.":[98],"Our":[99],"achieves":[101],"relative":[103],"reduction":[104],"in":[105,118],"character":[106],"error":[107],"rate":[108],"18%":[110],"compared":[111],"simple":[113],"full":[114,132],"method,":[116],"especially":[117],"speaker":[120],"adaptation":[121],"scenario,":[122],"while":[123],"only":[125],"half":[126],"training":[128],"parameters":[129],"required":[130],"fine-tuning.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}