{"id":"https://openalex.org/W7155403151","doi":"https://doi.org/10.48448/np5j-1093","title":"Effects of Speaker Bias in Dialect Identification and Automatic Transcription with Self-Supervised Speech Models","display_name":"Effects of Speaker Bias in Dialect Identification and Automatic Transcription with Self-Supervised Speech Models","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7155403151","doi":"https://doi.org/10.48448/np5j-1093"},"language":"en","primary_location":{"id":"doi:10.48448/np5j-1093","doi":"https://doi.org/10.48448/np5j-1093","is_oa":true,"landing_page_url":"https://doi.org/10.48448/np5j-1093","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"volume":null,"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48448/np5j-1093","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134424196","display_name":"Association for Computational Linguistics 2026","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Association for Computational Linguistics 2026","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5012702158","display_name":"Olli Kuparinen","orcid":"https://orcid.org/0000-0001-9468-7111","observed_orcids":["https://orcid.org/0000-0001-9468-7111"]},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Kuparinen, Olli","raw_affiliation_strings":["Tampere University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976000189781189,"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":0.9976000189781189,"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/T10860","display_name":"Speech and Audio Processing","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/dialect-identification","display_name":"dialect identification","score":0.9869999885559082},{"id":"https://openalex.org/keywords/self-supervised-speech-models","display_name":"self-supervised speech models","score":0.9120000004768372},{"id":"https://openalex.org/keywords/dialectology","display_name":"dialectology","score":0.6159999966621399},{"id":"https://openalex.org/keywords/voice-conversion","display_name":"voice conversion","score":0.6380000114440918},{"id":"https://openalex.org/keywords/pitch-shift","display_name":"pitch shifting","score":0.7509999871253967},{"id":"https://openalex.org/keywords/noise-augmentation","display_name":"noise augmentation","score":0.8429999947547913},{"id":"https://openalex.org/keywords/finnish-dialects","display_name":"Finnish dialects","score":0.9110000133514404},{"id":"https://openalex.org/keywords/norwegian-dialects","display_name":"Norwegian dialects","score":0.9990000128746033}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7105000019073486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7016000151634216},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6539999842643738},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.6129000186920166},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.553600013256073},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48420000076293945},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4595000147819519},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.45680001378059387},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4417000114917755},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.43939998745918274},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.438400000333786},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4142000079154968},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.351500004529953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34709998965263367},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2786000072956085},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C2987567764","wikidata":"https://www.wikidata.org/wiki/Q125421","display_name":"Second language","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48448/np5j-1093","doi":"https://doi.org/10.48448/np5j-1093","is_oa":true,"landing_page_url":"https://doi.org/10.48448/np5j-1093","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"doi:10.48448/np5j-1093","doi":"https://doi.org/10.48448/np5j-1093","is_oa":true,"landing_page_url":"https://doi.org/10.48448/np5j-1093","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2737312836","https://openalex.org/W7134926970","https://openalex.org/W4404781065","https://openalex.org/W7166512107","https://openalex.org/W6967003463","https://openalex.org/W2146591867","https://openalex.org/W7213998333","https://openalex.org/W1529116532","https://openalex.org/W3198689362","https://openalex.org/W4406343903"],"abstract_inverted_index":{"A":[0],"major":[1,181],"issue":[2],"in":[3,9,45,68,87,96,103,120],"audio":[4,137,176],"modeling":[5],"is":[6,36,43],"speaker":[7,66,93,112,117,166],"bias,":[8,167],"which":[10,97],"the":[11,63,100,130,135,147,158,187],"models":[12,161,172],"learn":[13],"language":[14,33],"external":[15],"traits,":[16],"such":[17],"as":[18,28,41,143,145],"a":[19,29,32,50,54,92,111],"speaker's":[20],"timbre":[21],"or":[22,189],"pitch,":[23],"and":[24,74,89,106,109,141],"use":[25],"this":[26,59],"information":[27],"short-cut":[30],"to":[31],"task.":[34],"This":[35],"especially":[37],"problematic":[38],"for":[39,184],"dialectology,":[40],"it":[42],"typical":[44],"dialect":[46,56,72,85,159],"corpora":[47],"that":[48,157],"only":[49,118],"few":[51],"speakers":[52,101],"represent":[53],"complete":[55],"area.":[57],"In":[58],"paper,":[60],"we":[61],"explore":[62],"effects":[64],"of":[65,84,99,129,186],"bias":[67],"two":[69,80],"dialectal":[70,76,170],"tasks:":[71],"identification":[73,160],"automatic":[75,169],"transcription.":[77],"We":[78,124,155],"build":[79],"different":[81],"data":[82,132],"partitions":[83],"interviews":[86],"Finnish":[88],"Norwegian:":[90],"1)":[91],"dependent":[94],"partition":[95,114],"all":[98],"appear":[102],"training,":[104],"development,":[105],"test":[107],"sets,":[108],"2)":[110],"independent":[113],"where":[115],"each":[116],"appears":[119],"exactly":[121],"one":[122],"set.":[123],"further":[125],"experiment":[126],"with":[127,138,151],"modifications":[128,177],"training":[131],"by":[133,165],"augmenting":[134],"original":[136,148],"pitch":[139],"shifts":[140],"noise,":[142],"well":[144],"changing":[146],"speakers'":[149],"voices":[150],"voice":[152],"conversion":[153],"models.":[154],"show":[156],"are":[162,173],"highly":[163],"effected":[164],"whereas":[168],"transcription":[171],"not.":[174],"The":[175],"do":[178],"not":[179],"offer":[180],"performance":[182],"gains":[183],"either":[185],"languages":[188],"tasks.":[190]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-04-24T00:00:00"}