{"id":"https://openalex.org/W4416798825","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249367","title":"Dialect Identification Using Resource-Efficient Fine-Tuning Approaches","display_name":"Dialect Identification Using Resource-Efficient Fine-Tuning Approaches","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798825","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249367"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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":"https://openalex.org/A5101348630","display_name":"Zirui Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Zirui Lin","raw_affiliation_strings":["School of Engineering, Institute of Science Tokyo,Dept. of Systems and Control Engineering,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, Institute of Science Tokyo,Dept. of Systems and Control Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045989070","display_name":"Haris Gulzar","orcid":"https://orcid.org/0000-0002-1677-2190"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haris Gulzar","raw_affiliation_strings":["NTT Software Innovation Center,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Software Innovation Center,Tokyo,Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120482176","display_name":"Monnika Roslianna Busto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Monnika Roslianna Busto","raw_affiliation_strings":["NTT Software Innovation Center,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Software Innovation Center,Tokyo,Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075274684","display_name":"Akiko Masaki","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Akiko Masaki","raw_affiliation_strings":["NTT Software Innovation Center,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Software Innovation Center,Tokyo,Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019776988","display_name":"Takeharu Eda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takeharu Eda","raw_affiliation_strings":["NTT Software Innovation Center,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Software Innovation Center,Tokyo,Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041970584","display_name":"Kazuhiro Nakadai","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Nakadai","raw_affiliation_strings":["School of Engineering, Institute of Science Tokyo,Dept. of Systems and Control Engineering,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering, Institute of Science Tokyo,Dept. of Systems and Control Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17635353,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"670","last_page":"675"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6547999978065491,"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":0.6547999978065491,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.18809999525547028,"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/T11640","display_name":"Linguistic Variation and Morphology","score":0.027899999171495438,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6381999850273132},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6323999762535095},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.567300021648407},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5385000109672546},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.47540000081062317},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.3871999979019165},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.375},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3479999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8374999761581421},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6381999850273132},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6323999762535095},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5968999862670898},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.567300021648407},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5385000109672546},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5059000253677368},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.491100013256073},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.47540000081062317},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.3871999979019165},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.375},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C2994428975","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word identification","level":4,"score":0.31619998812675476},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.28949999809265137},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.28690001368522644},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2655999958515167},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249367","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249367","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1491198847","https://openalex.org/W2091409162","https://openalex.org/W2130721836","https://openalex.org/W2210153255","https://openalex.org/W3016021175","https://openalex.org/W3097777922","https://openalex.org/W3153675281","https://openalex.org/W3176828726","https://openalex.org/W3202370288","https://openalex.org/W4225274946","https://openalex.org/W4385245566","https://openalex.org/W4385570973","https://openalex.org/W4385823097","https://openalex.org/W4391420283","https://openalex.org/W4392605639","https://openalex.org/W4392902822","https://openalex.org/W4392903886","https://openalex.org/W4402670040","https://openalex.org/W4402754293","https://openalex.org/W4402961769","https://openalex.org/W4405633822"],"related_works":[],"abstract_inverted_index":{"Dialect":[0],"Identification":[1],"(DI)":[2],"is":[3,44],"a":[4,15,32,37,125,155],"task":[5],"to":[6,21,102,133,148,163],"recognize":[7],"different":[8],"dialects":[9],"within":[10],"the":[11,23,103,112,130,139],"same":[12],"language":[13,97],"from":[14,138],"speech":[16,25,38,60,106],"signal.":[17],"DI":[18,43,65],"can":[19],"help":[20],"improve":[22],"downstream":[24],"related":[26],"tasks":[27,41,63],"even":[28],"when":[29],"speakers":[30],"have":[31,56],"strong":[33],"dialect.":[34],"However,":[35],"fine-tuning":[36,58,117,165],"model":[39,132],"for":[40,62,96],"like":[42,64],"expensive":[45],"in":[46,78],"terms":[47],"of":[48,157],"computation":[49],"cost":[50],"and":[51,81,99,116,150,166],"memory":[52,79,114,144],"requirement.":[53],"Recent":[54],"studies":[55],"explored":[57],"pre-trained":[59,105],"models":[61],"using":[66],"Parameter-Efficient":[67],"Fine-Tuning":[68,91],"(PEFT)":[69],"methods,":[70,93],"which":[71],"offer":[72],"parameter":[73],"efficiency":[74,80],"but":[75],"limited":[76],"improvement":[77],"training":[82,152],"speed.":[83],"To":[84],"address":[85],"these":[86],"challenges,":[87],"we":[88,128],"explore":[89],"Memory-Efficient":[90],"(MEFT)":[92],"originally":[94],"proposed":[95],"processing,":[98],"apply":[100],"them":[101],"generalpurpose":[104],"model.":[107],"We":[108],"then":[109],"comprehensively":[110],"analyze":[111],"GPU":[113,143],"usage":[115,145],"speed":[118,153],"based":[119],"on":[120],"various":[121],"MEFT":[122],"methods.":[123,168],"As":[124],"case":[126],"study,":[127],"fine-tune":[129],"Whisper":[131],"identify":[134],"six":[135],"Mandarin":[136],"subdialects":[137],"KeSpeech":[140],"dataset,":[141],"reducing":[142],"by":[146,154],"up":[147],"73.25%":[149],"accelerating":[151],"factor":[156],"2.1,":[158],"while":[159],"maintaining":[160],"accuracy":[161],"comparable":[162],"vanilla":[164],"PEFT":[167]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}