{"id":"https://openalex.org/W4400397471","doi":"https://doi.org/10.1145/3640794.3665579","title":"\"\u00bfTe vienes? Sure!\" Joint Fine-tuning of Language Detection and Transcription Improves Automatic Recognition of Code-Switching Speech","display_name":"\"\u00bfTe vienes? Sure!\" Joint Fine-tuning of Language Detection and Transcription Improves Automatic Recognition of Code-Switching Speech","publication_year":2024,"publication_date":"2024-07-07","ids":{"openalex":"https://openalex.org/W4400397471","doi":"https://doi.org/10.1145/3640794.3665579"},"language":"en","primary_location":{"id":"doi:10.1145/3640794.3665579","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640794.3665579","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Conversational User Interfaces 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3640794.3665579","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100046337","display_name":"Leopold Hillah","orcid":"https://orcid.org/0009-0006-5229-468X"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":true,"raw_author_name":"Leopold Hillah","raw_affiliation_strings":["Department of Computer Science, University of Luxembourg, Luxembourg"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072485983","display_name":"Mateusz Dubiel","orcid":"https://orcid.org/0000-0001-8250-3370"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Mateusz Dubiel","raw_affiliation_strings":["University of Luxembourg, Luxembourg"],"affiliations":[{"raw_affiliation_string":"University of Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017930924","display_name":"Luis A. Leiva","orcid":"https://orcid.org/0000-0002-5011-1847"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Luis A. Leiva","raw_affiliation_strings":["University of Luxembourg, Luxembourg","MATEUSZ DUBIEL, University of Luxembourg, Luxembourg"],"affiliations":[{"raw_affiliation_string":"University of Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]},{"raw_affiliation_string":"MATEUSZ DUBIEL, University of Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100046337"],"corresponding_institution_ids":["https://openalex.org/I186903577"],"apc_list":null,"apc_paid":null,"fwci":0.3599,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57554314,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13155","display_name":"Digital Communication and Language","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T13155","display_name":"Digital Communication and Language","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T12031","display_name":"Speech and dialogue systems","score":0.98580002784729,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9815999865531921,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7730412483215332},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6355712413787842},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5810793042182922},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5458595752716064},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.4635334312915802},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.43876099586486816},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41756904125213623},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3758852183818817},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3431991934776306},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33418402075767517},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.25009721517562866},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09976670145988464},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08654046058654785}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7730412483215332},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6355712413787842},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5810793042182922},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5458595752716064},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.4635334312915802},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.43876099586486816},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41756904125213623},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3758852183818817},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3431991934776306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33418402075767517},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25009721517562866},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09976670145988464},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08654046058654785},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3640794.3665579","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640794.3665579","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Conversational User Interfaces 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:orbilu.uni.lu:10993/61597","is_oa":true,"landing_page_url":"https://orbilu.uni.lu/handle/10993/61597","pdf_url":"https://orbilu.uni.lu/bitstream/10993/61597/1/Joint_Fine_tuning_of_Language_Detection_and_ASR_for_Code_Switching_Speech.pdf","source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 6th ACM Conference on Conversational User Interfaces (2024-07-08); CUI '24: 6th ACM Conference on Conversational User Interfaces, Luxembourg City, Luxembourg [LU], from 8 to 10 July 2024","raw_type":"peer reviewed"}],"best_oa_location":{"id":"doi:10.1145/3640794.3665579","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3640794.3665579","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Conversational User Interfaces 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[{"id":"https://openalex.org/G2045231469","display_name":null,"funder_award_id":"SYMBIOTIK","funder_id":"https://openalex.org/F4320338448","funder_display_name":"HORIZON EUROPE European Innovation Council"},{"id":"https://openalex.org/G439031883","display_name":null,"funder_award_id":"101071147","funder_id":"https://openalex.org/F4320338448","funder_display_name":"HORIZON EUROPE European Innovation Council"},{"id":"https://openalex.org/G5509659972","display_name":null,"funder_award_id":"CHIST-ERA","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7561857167","display_name":null,"funder_award_id":"CHIST-ERA-20-BCI-001","funder_id":"https://openalex.org/F4320338463","funder_display_name":"CHIST-ERA"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8947675394","display_name":"Context-aware adaptive visualizations for critical decision making","funder_award_id":"101071147","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320338448","display_name":"HORIZON EUROPE European Innovation Council","ror":null},{"id":"https://openalex.org/F4320338463","display_name":"CHIST-ERA","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W754909321","https://openalex.org/W2023946512","https://openalex.org/W2078834097","https://openalex.org/W2250548009","https://openalex.org/W2743691218","https://openalex.org/W2803339164","https://openalex.org/W2896558859","https://openalex.org/W3034935844","https://openalex.org/W3036601975","https://openalex.org/W3096032230","https://openalex.org/W3100584004","https://openalex.org/W3100756752","https://openalex.org/W3139878283","https://openalex.org/W3144847677","https://openalex.org/W3147984406","https://openalex.org/W3163937874","https://openalex.org/W4210463634","https://openalex.org/W4214534271","https://openalex.org/W4283327263","https://openalex.org/W4295955231","https://openalex.org/W4312054229","https://openalex.org/W4366549933","https://openalex.org/W4385570104","https://openalex.org/W4385573164","https://openalex.org/W4391021723"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340","https://openalex.org/W4229451372"],"abstract_inverted_index":{"Human":[0],"communication":[1],"in":[2,18,99],"multilingual":[3],"communities":[4],"often":[5],"leads":[6],"to":[7,30,67,126],"code-switching,":[8],"where":[9],"individuals":[10],"seamlessly":[11],"alternate":[12],"between":[13,103],"two":[14],"or":[15],"more":[16],"languages":[17],"their":[19],"daily":[20],"interactions.":[21],"While":[22],"this":[23,58,69],"phenomenon":[24],"has":[25],"been":[26],"increasingly":[27],"prevalent":[28],"thanks":[29],"linguistic":[31],"globalization,":[32],"it":[33],"presents":[34],"challenges":[35],"for":[36,118],"Automatic":[37],"Speech":[38],"Recognition":[39],"(ASR)":[40],"systems":[41],"since":[42],"they":[43],"are":[44],"designed":[45],"with":[46],"the":[47,73,86],"assumption":[48],"of":[49,88,109,130],"transcribing":[50],"a":[51,55,62,115],"single":[52],"language":[53,79],"at":[54],"time.":[56],"In":[57],"work,":[59],"we":[60],"propose":[61],"simple":[63],"yet":[64],"unexplored":[65],"approach":[66],"tackle":[68],"challenge":[70],"by":[71],"fine-tuning":[72],"Whisper":[74],"pre-trained":[75],"model":[76],"jointly":[77],"on":[78,120],"identification":[80],"(LID)":[81],"and":[82,105],"transcription":[83,100],"tasks":[84],"through":[85],"introduction":[87],"an":[89,124],"auxiliary":[90],"LID":[91],"loss":[92],"term.":[93],"Our":[94],"results":[95],"show":[96],"significant":[97],"improvements":[98],"errors,":[101],"ranging":[102],"14":[104],"36":[106],"percentage":[107],"points":[108],"difference.":[110],"Ultimately,":[111],"our":[112],"work":[113],"opens":[114],"new":[116],"direction":[117],"research":[119],"code-switching":[121],"speech,":[122],"offering":[123],"opportunity":[125],"enhance":[127],"current":[128],"capabilities":[129],"conversational":[131],"agents.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}
