{"id":"https://openalex.org/W4416746199","doi":"https://doi.org/10.1016/j.csl.2025.101905","title":"Do modern speech LLMs and re-scoring techniques improve bilingual ASR performance for Basque and Spanish in domain-specific contexts?","display_name":"Do modern speech LLMs and re-scoring techniques improve bilingual ASR performance for Basque and Spanish in domain-specific contexts?","publication_year":2025,"publication_date":"2025-11-27","ids":{"openalex":"https://openalex.org/W4416746199","doi":"https://doi.org/10.1016/j.csl.2025.101905"},"language":"en","primary_location":{"id":"doi:10.1016/j.csl.2025.101905","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.csl.2025.101905","pdf_url":null,"source":{"id":"https://openalex.org/S91252481","display_name":"Computer Speech & Language","issn_l":"0885-2308","issn":["0885-2308","1095-8363"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Speech &amp; Language","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.csl.2025.101905","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002565184","display_name":"Ander Gonz\u00e1lez-Docasal","orcid":"https://orcid.org/0000-0003-3585-6346"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]},{"id":"https://openalex.org/I4210092551","display_name":"Vicomtech","ror":"https://ror.org/0023sah13","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210092551"]},{"id":"https://openalex.org/I4210150815","display_name":"Instituto Tecnol\u00f3gico de Arag\u00f3n","ror":"https://ror.org/05sep9w93","country_code":"ES","type":"other","lineage":["https://openalex.org/I4210150815"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Ander Gonz\u00e1lez-Docasal","raw_affiliation_strings":["Aragon Institute for Engineering Research, University of Zaragoza, Mariano Esquillor, Zaragoza, 50018, Spain","Fundaci\u00f3n Vicomtech, Basque Research and Technology Alliance (BRTA), Mikeletegi 57, Donostia - San Sebasti\u00e1n, 20009, Gipuzkoa, Spain"],"affiliations":[{"raw_affiliation_string":"Aragon Institute for Engineering Research, University of Zaragoza, Mariano Esquillor, Zaragoza, 50018, Spain","institution_ids":["https://openalex.org/I255234318","https://openalex.org/I4210150815"]},{"raw_affiliation_string":"Fundaci\u00f3n Vicomtech, Basque Research and Technology Alliance (BRTA), Mikeletegi 57, Donostia - San Sebasti\u00e1n, 20009, Gipuzkoa, Spain","institution_ids":["https://openalex.org/I4210092551"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073624805","display_name":"Juan Camilo V\u00e1squez-Correa","orcid":"https://orcid.org/0000-0003-4946-9232"},"institutions":[{"id":"https://openalex.org/I4210092551","display_name":"Vicomtech","ror":"https://ror.org/0023sah13","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210092551"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Juan Camilo V\u00e1squez-Correa","raw_affiliation_strings":["Fundaci\u00f3n Vicomtech, Basque Research and Technology Alliance (BRTA), Mikeletegi 57, Donostia - San Sebasti\u00e1n, 20009, Gipuzkoa, Spain"],"affiliations":[{"raw_affiliation_string":"Fundaci\u00f3n Vicomtech, Basque Research and Technology Alliance (BRTA), Mikeletegi 57, Donostia - San Sebasti\u00e1n, 20009, Gipuzkoa, Spain","institution_ids":["https://openalex.org/I4210092551"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000869612","display_name":"Haritz Arzelus","orcid":"https://orcid.org/0000-0002-0731-1317"},"institutions":[{"id":"https://openalex.org/I4210092551","display_name":"Vicomtech","ror":"https://ror.org/0023sah13","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210092551"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Haritz Arzelus","raw_affiliation_strings":["Fundaci\u00f3n Vicomtech, Basque Research and Technology Alliance (BRTA), Mikeletegi 57, Donostia - San Sebasti\u00e1n, 20009, Gipuzkoa, Spain"],"affiliations":[{"raw_affiliation_string":"Fundaci\u00f3n Vicomtech, Basque Research and Technology Alliance (BRTA), Mikeletegi 57, Donostia - San Sebasti\u00e1n, 20009, Gipuzkoa, Spain","institution_ids":["https://openalex.org/I4210092551"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063619413","display_name":"Aitor \u00c1lvarez","orcid":"https://orcid.org/0000-0002-7938-4486"},"institutions":[{"id":"https://openalex.org/I4210092551","display_name":"Vicomtech","ror":"https://ror.org/0023sah13","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210092551"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Aitor \u00c1lvarez","raw_affiliation_strings":["Fundaci\u00f3n Vicomtech, Basque Research and Technology Alliance (BRTA), Mikeletegi 57, Donostia - San Sebasti\u00e1n, 20009, Gipuzkoa, Spain"],"affiliations":[{"raw_affiliation_string":"Fundaci\u00f3n Vicomtech, Basque Research and Technology Alliance (BRTA), Mikeletegi 57, Donostia - San Sebasti\u00e1n, 20009, Gipuzkoa, Spain","institution_ids":["https://openalex.org/I4210092551"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009047384","display_name":"S. A. Moreno-Acevedo","orcid":"https://orcid.org/0000-0001-7300-8562"},"institutions":[{"id":"https://openalex.org/I4210092551","display_name":"Vicomtech","ror":"https://ror.org/0023sah13","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210092551"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Santiago A. Moreno-Acevedo","raw_affiliation_strings":["Fundaci\u00f3n Vicomtech, Basque Research and Technology Alliance (BRTA), Mikeletegi 57, Donostia - San Sebasti\u00e1n, 20009, Gipuzkoa, Spain"],"affiliations":[{"raw_affiliation_string":"Fundaci\u00f3n Vicomtech, Basque Research and Technology Alliance (BRTA), Mikeletegi 57, Donostia - San Sebasti\u00e1n, 20009, Gipuzkoa, Spain","institution_ids":["https://openalex.org/I4210092551"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5002565184"],"corresponding_institution_ids":["https://openalex.org/I255234318","https://openalex.org/I4210092551","https://openalex.org/I4210150815"],"apc_list":{"value":3400,"currency":"USD","value_usd":3400},"apc_paid":{"value":3400,"currency":"USD","value_usd":3400},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19278701,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"99","issue":null,"first_page":"101905","last_page":"101905"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9398999810218811,"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":0.9398999810218811,"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":0.006200000178068876,"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/T10863","display_name":"Voice and Speech Disorders","score":0.00559999980032444,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6647999882698059},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5770000219345093},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5638999938964844},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5526999831199646},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4878000020980835},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.45260000228881836},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.39989998936653137},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3490999937057495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8819000124931335},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6647999882698059},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5942000150680542},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5770000219345093},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5638999938964844},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5526999831199646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5074999928474426},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5026000142097473},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4878000020980835},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.45260000228881836},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.33169999718666077},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25690001249313354},{"id":"https://openalex.org/C2781440851","wikidata":"https://www.wikidata.org/wiki/Q35749","display_name":"Parliament","level":3,"score":0.2524000108242035}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.csl.2025.101905","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.csl.2025.101905","pdf_url":null,"source":{"id":"https://openalex.org/S91252481","display_name":"Computer Speech & Language","issn_l":"0885-2308","issn":["0885-2308","1095-8363"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Speech &amp; Language","raw_type":"journal-article"},{"id":"pmh:oai:zaguan.unizar.es:165231","is_oa":true,"landing_page_url":"http://zaguan.unizar.es/record/165231","pdf_url":null,"source":{"id":"https://openalex.org/S4306401812","display_name":"Zaguan (University of Zaragoza Repository)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I255234318","host_organization_name":"Universidad de Zaragoza","host_organization_lineage":["https://openalex.org/I255234318"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1016/j.csl.2025.101905","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.csl.2025.101905","pdf_url":null,"source":{"id":"https://openalex.org/S91252481","display_name":"Computer Speech & Language","issn_l":"0885-2308","issn":["0885-2308","1095-8363"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Speech &amp; Language","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3358026839","display_name":null,"funder_award_id":"KK-2024/00050","funder_id":"https://openalex.org/F4320321705","funder_display_name":"Eusko Jaurlaritza"}],"funders":[{"id":"https://openalex.org/F4320321705","display_name":"Eusko Jaurlaritza","ror":"https://ror.org/00pz2fp31"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W175761898","https://openalex.org/W2127141656","https://openalex.org/W2158195707","https://openalex.org/W2160815625","https://openalex.org/W3135169209","https://openalex.org/W3210615406","https://openalex.org/W3211278025","https://openalex.org/W4392100823","https://openalex.org/W4392201601","https://openalex.org/W4402112461","https://openalex.org/W4402115972","https://openalex.org/W4402774103","https://openalex.org/W4404066786","https://openalex.org/W4404067578","https://openalex.org/W4407638156","https://openalex.org/W4408565363"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"extended":[4],"evaluation":[5],"of":[6,61,69,79,108,147],"Vicomtech\u2019s":[7],"automatic":[8,109],"speech":[9],"recognition":[10,200],"(ASR)":[11],"systems":[12,94,157],"developed":[13],"for":[14,64],"the":[15,54,58,67,89,93,140,145,208],"Albayz\u00edn":[16],"2024":[17],"Bilingual":[18],"Basque-Spanish":[19],"Speech-to-Text":[20],"(BBS-S2T)":[21],"Challenge,":[22],"a":[23,98,162],"task":[24],"focused":[25],"on":[26,88,97,161],"transcribing":[27],"bilingual":[28,164],"parliamentary":[29],"recordings":[30],"featuring":[31],"frequent":[32],"intra-":[33],"and":[34,39,66,71,85,118,168,175,191],"inter-sentential":[35],"code-switching":[36,152],"between":[37],"Basque":[38,45],"Spanish.":[40],"These":[41],"recordings,":[42],"drawn":[43],"from":[44],"Parliament":[46],"plenary":[47],"sessions,":[48],"pose":[49],"significant":[50],"challenges":[51],"due":[52],"to":[53,101,197],"abrupt":[55],"language":[56,120,177,181],"alternations,":[57],"limited":[59],"availability":[60],"digital":[62],"resources":[63],"Basque,":[65],"absence":[68],"contextual":[70],"speaker":[72],"information.":[73],"The":[74],"study":[75],"incorporates":[76],"additional":[77],"analysis":[78,193],"state-of-the-art":[80],"ASR":[81,149,156],"architectures,":[82],"namely":[83],"Phi4-multimodal":[84],"CrisperWhisper,":[86],"fine-tuned":[87],"challenge":[90],"dataset.":[91],"Furthermore,":[92],"were":[95,171],"evaluated":[96],"complementary":[99],"benchmark":[100],"assess":[102],"model":[103,121],"robustness.":[104],"A":[105],"detailed":[106],"comparison":[107],"hypothesis":[110],"selection":[111],"techniques,":[112],"including":[113],"both":[114],"traditional":[115],"n":[116],"-gram":[117],"large":[119,176],"(LLM)-based":[122],"approaches,":[123],"is":[124],"also":[125],"provided.":[126],"Results":[127],"demonstrate":[128],"that":[129],"optimal":[130],"word":[131],"error":[132],"rate":[133],"(WER)":[134],"does":[135],"not":[136,206],"always":[137],"correlate":[138],"with":[139],"most":[141],"accurate":[142],"transcriptions,":[143],"highlighting":[144],"complexity":[146],"evaluating":[148],"performance":[150],"in":[151,212],"scenarios.":[153],"\u2022":[154,166,179,188,202],"Leading":[155],"have":[158],"been":[159,195],"assessed":[160],"challenging":[163],"domain.":[165],"Fusion":[167],"re-scoring":[169],"frameworks":[170],"applied":[172],"using":[173],"statistical":[174],"models.":[178],"External":[180],"models":[182],"prioritised":[183],"meaning":[184],"over":[185],"transcription":[186],"accuracy.":[187],"An":[189],"extensive":[190],"dedicated":[192],"had":[194],"performed":[196],"further":[198],"evaluate":[199],"errors.":[201],"Optimal":[203],"WER":[204],"may":[205],"reflect":[207],"top":[209],"quality":[210],"transcriptions":[211],"specific":[213],"applications.":[214]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}
