{"id":"https://openalex.org/W4415433426","doi":"https://doi.org/10.21437/interspeech.2025-1078","title":"Optimizing ASR for Catalan-Spanish Code-Switching: A Comparative Analysis of Methodologies","display_name":"Optimizing ASR for Catalan-Spanish Code-Switching: A Comparative Analysis of Methodologies","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433426","doi":"https://doi.org/10.21437/interspeech.2025-1078"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1078","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/2117/458972","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027493604","display_name":"Carlos Mena","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carlos Mena","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Pol Serra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pol Serra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jacobo Romero","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jacobo Romero","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090097636","display_name":"Abir Messaoudi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abir Messaoudi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002515502","display_name":"Jos\u00e9 Joaqu\u00edn Montes Giraldo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jose Giraldo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049663811","display_name":"Carme Armentano-Oller","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carme Armentano-Oller","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006038779","display_name":"Rodolfo Zevallos","orcid":"https://orcid.org/0000-0003-0192-7740"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rodolfo Zevallos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120093874","display_name":"Ivan Meza","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivan Meza","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5025633053","display_name":"Javier Hernando","orcid":"https://orcid.org/0000-0002-1730-8154"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Javier Hernando","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4298","last_page":"4302"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9634000062942505,"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/T12031","display_name":"Speech and dialogue systems","score":0.9634000062942505,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9488999843597412,"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/key","display_name":"Key (lock)","score":0.27549999952316284},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2653000056743622},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2387000024318695},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.2345000058412552},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.2224999964237213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5834000110626221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3921000063419342},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2387000024318695},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2345000058412552},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2224999964237213},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.21150000393390656},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.20909999310970306},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.20669999718666077}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-1078","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/458972","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/458972","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"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":null,"raw_type":"Conference report"}],"best_oa_location":{"id":"pmh:oai:upcommons.upc.edu:2117/458972","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/458972","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"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":null,"raw_type":"Conference report"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321505","display_name":"Generalitat de Catalunya","ror":"https://ror.org/01bg62x04"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Code-switching":[0],"(CS),":[1],"the":[2,138,143],"alternating":[3],"use":[4],"of":[5,25,133],"two":[6],"or":[7,38],"more":[8],"languages,":[9],"challenges":[10],"automatic":[11],"speech":[12,113],"recognition":[13],"(ASR)":[14],"due":[15],"to":[16,43],"scarce":[17],"training":[18],"data":[19,103,110,136],"and":[20,60,73,98,115],"linguistic":[21],"similarities.":[22],"The":[23],"lack":[24],"dedicated":[26],"CS":[27,46,56,84,92,102,109,135],"datasets":[28],"limits":[29],"ASR":[30,81],"performance,":[31],"as":[32],"most":[33],"models":[34],"rely":[35],"on":[36,123],"monolingual":[37,96],"mixed-language":[39],"corpora":[40,114],"that":[41,128],"fail":[42],"reflect":[44],"real-world":[45],"patterns.":[47],"This":[48],"issue":[49],"is":[50,66],"critical":[51],"in":[52,58,71],"multilingual":[53],"societies":[54],"where":[55],"occurs":[57],"informal":[59],"formal":[61],"settings.":[62],"A":[63],"key":[64],"example":[65],"Catalan-Spanish":[67,83],"CS,":[68],"widely":[69],"used":[70],"media":[72],"parliamentary":[74],"speeches.":[75],"In":[76],"this":[77],"work,":[78],"we":[79],"improve":[80],"for":[82],"by":[85],"exploring":[86],"three":[87],"strategies:":[88],"(1)":[89],"generating":[90],"synthetic":[91,134],"data,":[93],"(2)":[94],"concatenating":[95],"audio,":[97],"(3)":[99],"leveraging":[100],"real":[101],"with":[104,137],"language":[105,140],"tokens.":[106],"We":[107],"extract":[108],"from":[111],"Catalan":[112],"fine-tune":[116],"OpenAI\u2019s":[117],"Whisper":[118],"models,":[119],"making":[120],"them":[121],"available":[122],"Hugging":[124],"Face.":[125],"Results":[126],"show":[127],"combining":[129],"a":[130],"modest":[131],"amount":[132],"dominant":[139],"token":[141],"yields":[142],"best":[144],"transcription":[145],"performance.":[146]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-24T00:00:00"}
