{"id":"https://openalex.org/W4408355083","doi":"https://doi.org/10.1109/icassp49660.2025.10890166","title":"Developing a Multilingual Dataset and Evaluation Metrics for Code-Switching: A Focus on Hong Kong\u2019s Polylingual Dynamics","display_name":"Developing a Multilingual Dataset and Evaluation Metrics for Code-Switching: A Focus on Hong Kong\u2019s Polylingual Dynamics","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355083","doi":"https://doi.org/10.1109/icassp49660.2025.10890166"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101512321","display_name":"Peng Xie","orcid":"https://orcid.org/0009-0008-1545-9048"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Peng Xie","raw_affiliation_strings":["The Hong Kong University of Science and Technology,Department of Computer Science and Engineering,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology,Department of Computer Science and Engineering,Hong Kong,China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040402090","display_name":"Kani Chen","orcid":"https://orcid.org/0000-0003-0117-8065"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kani Chen","raw_affiliation_strings":["The Hong Kong University of Science and Technology,Department of Mathematics,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology,Department of Mathematics,Hong Kong,China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10265","display_name":"Multilingual Education and Policy","score":0.9797999858856201,"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"}},"topics":[{"id":"https://openalex.org/T10265","display_name":"Multilingual Education and Policy","score":0.9797999858856201,"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"}},{"id":"https://openalex.org/T12542","display_name":"Second Language Learning and Teaching","score":0.9164000153541565,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.8063769340515137},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7303174734115601},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.5838865637779236},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5755574703216553},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.5700408220291138},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2763892710208893},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16290175914764404},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.12541797757148743}],"concepts":[{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.8063769340515137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7303174734115601},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.5838865637779236},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5755574703216553},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.5700408220291138},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2763892710208893},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16290175914764404},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.12541797757148743},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-147935","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-147935","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W754909321","https://openalex.org/W1986585666","https://openalex.org/W2092910593","https://openalex.org/W2095734449","https://openalex.org/W2161490380","https://openalex.org/W2399344342","https://openalex.org/W3161873870","https://openalex.org/W3204696009","https://openalex.org/W4385572634","https://openalex.org/W4387835442","https://openalex.org/W6678759501","https://openalex.org/W6767671539","https://openalex.org/W6771467084","https://openalex.org/W6778154085","https://openalex.org/W6790121257","https://openalex.org/W6811717302","https://openalex.org/W6847363464","https://openalex.org/W6851513886","https://openalex.org/W6852874933"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2771594921","https://openalex.org/W2432897346","https://openalex.org/W2181336723","https://openalex.org/W4389976243","https://openalex.org/W3158134258","https://openalex.org/W3138119129","https://openalex.org/W2940588741"],"abstract_inverted_index":{"The":[0,93],"existing":[1],"audio":[2,65],"datasets":[3],"are":[4],"predominantly":[5],"tailored":[6],"towards":[7],"single":[8],"languages,":[9],"overlooking":[10],"the":[11,75,85,118,130],"complex":[12],"linguistic":[13],"behaviors":[14],"of":[15,57,132],"multilingual":[16,40,77],"communities":[17],"that":[18],"engage":[19],"in":[20,32,39,102],"code-switching.":[21],"This":[22,125],"practice,":[23],"where":[24],"individuals":[25],"frequently":[26],"mix":[27],"two":[28],"or":[29],"more":[30],"languages":[31],"their":[33],"daily":[34],"interactions,":[35],"is":[36],"particularly":[37],"prevalent":[38],"regions":[41],"such":[42,99],"as":[43,100],"Hong":[44],"Kong,":[45],"China.":[46],"To":[47],"bridge":[48],"this":[49],"gap,":[50],"we":[51],"have":[52,109],"developed":[53],"a":[54,111],"34.8-hour":[55],"dataset":[56],"Mixed":[58],"Cantonese":[59],"and":[60,105,122],"English":[61],"(MCE<sup":[62],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[63],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>)":[64],"using":[66],"our":[67],"Multi-Agent":[68],"Data":[69],"Generation":[70],"Framework":[71],"(MADGF).":[72],"We":[73,108],"fine-tuned":[74],"open-source":[76],"Automatic":[78],"Speech":[79],"Recognition":[80],"(ASR)":[81],"model,":[82],"Whisper,":[83],"with":[84],"MCE":[86],"dataset,":[87],"leading":[88],"to":[89,117,128,136],"impressive":[90],"zero-shot":[91],"performance.":[92],"traditional":[94,133],"metrics":[95,134],"overlook":[96],"important":[97],"factors":[98],"latency":[101],"real-world":[103],"applications":[104],"code-switching":[106],"scenarios.":[107],"introduced":[110],"novel":[112],"evaluation":[113],"metric":[114,126],"called":[115],"Fidelity":[116],"Original":[119],"Audio,":[120],"Accuracy,":[121],"Latency":[123],"(FAL).":[124],"aims":[127],"overcome":[129],"limitations":[131],"used":[135],"assess":[137],"ASR":[138],"systems.":[139]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
