{"id":"https://openalex.org/W4409248323","doi":"https://doi.org/10.1109/icct62411.2024.10946392","title":"EMGL: Enhancing Mandarin-English Code-Switching Speech Recognition using Generative Labeling Technique","display_name":"EMGL: Enhancing Mandarin-English Code-Switching Speech Recognition using Generative Labeling Technique","publication_year":2024,"publication_date":"2024-10-18","ids":{"openalex":"https://openalex.org/W4409248323","doi":"https://doi.org/10.1109/icct62411.2024.10946392"},"language":"en","primary_location":{"id":"doi:10.1109/icct62411.2024.10946392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icct62411.2024.10946392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 24th International Conference on Communication Technology (ICCT)","raw_type":"proceedings-article"},"type":"article","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/A5069471244","display_name":"Zhentao Lin","orcid":"https://orcid.org/0000-0003-1977-2249"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhentao Lin","raw_affiliation_strings":["Guangdong University of Technology,Computer Science and Engineering,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434179","display_name":"Zihao Chen","orcid":"https://orcid.org/0000-0003-1224-5067"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihao Chen","raw_affiliation_strings":["Guangdong University of Technology,Computer Science and Engineering,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017218704","display_name":"Bi Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bi Zeng","raw_affiliation_strings":["Guangdong University of Technology,Computer Science and Engineering,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066373459","display_name":"Shengyu Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I890469752","display_name":"Ministry of Industry and Information Technology","ror":"https://ror.org/0385nmy68","country_code":"CN","type":"government","lineage":["https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengyu Wei","raw_affiliation_strings":["CEPREI IPTRKL of MIIT,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"CEPREI IPTRKL of MIIT,Guangzhou,China","institution_ids":["https://openalex.org/I890469752"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064490466","display_name":"Jia Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I890469752","display_name":"Ministry of Industry and Information Technology","ror":"https://ror.org/0385nmy68","country_code":"CN","type":"government","lineage":["https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Cai","raw_affiliation_strings":["CEPREI IPTRKL of MIIT,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"CEPREI IPTRKL of MIIT,Guangzhou,China","institution_ids":["https://openalex.org/I890469752"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003666821","display_name":"Shang Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shang Xiao","raw_affiliation_strings":["Guangdong University of Technology,Computer Science and Engineering,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"Guangdong University of Technology,Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I139024713"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5069471244"],"corresponding_institution_ids":["https://openalex.org/I139024713"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26862172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1433","last_page":"1440"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9666000008583069,"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":0.9666000008583069,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.740894079208374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7379511594772339},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6450663805007935},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.6346251368522644},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5291343927383423},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47057220339775085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3929818272590637},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20817312598228455}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.740894079208374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7379511594772339},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6450663805007935},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.6346251368522644},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5291343927383423},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47057220339775085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3929818272590637},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20817312598228455},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icct62411.2024.10946392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icct62411.2024.10946392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 24th International Conference on Communication Technology (ICCT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W197277712","https://openalex.org/W2996952407","https://openalex.org/W3035390927","https://openalex.org/W3097777922","https://openalex.org/W3197144816","https://openalex.org/W3198694222","https://openalex.org/W3203407300","https://openalex.org/W4283067311","https://openalex.org/W4312698052","https://openalex.org/W4319782172","https://openalex.org/W4372266937","https://openalex.org/W4385822890","https://openalex.org/W4408352239","https://openalex.org/W6780218876","https://openalex.org/W6810476118","https://openalex.org/W6845923821","https://openalex.org/W6847363464","https://openalex.org/W6848735303","https://openalex.org/W6857817883"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W2366752344"],"abstract_inverted_index":{"Mandarin-English":[0,75],"Code-Switching":[1],"Automatic":[2],"Speech":[3],"Recognition":[4],"(MECS-ASR)":[5],"is":[6,100],"significantly":[7,78],"impeded":[8],"by":[9],"limited":[10],"data":[11,27,128],"availability.":[12],"Previous":[13],"studies":[14],"have":[15],"demonstrated":[16],"only":[17],"marginal":[18],"improvements":[19],"in":[20,122,130,139],"performance,":[21],"even":[22],"with":[23],"the":[24,80,91,103,117,124],"implementation":[25],"of":[26,70,74,120,127,141],"augmentation,":[28],"pre-trained":[29],"models,":[30],"prompt":[31,111],"engineering,":[32],"and":[33,58],"multi-task":[34],"learning":[35],"strategies.":[36],"This":[37,98],"paper":[38],"presents":[39],"a":[40,67,85,133,137],"groundbreaking":[41],"approach,":[42],"Enhancing":[43],"MECS-ASR":[44,96],"using":[45],"Generative":[46],"Labeling":[47],"Technique":[48],"(EMGL),":[49],"which":[50],"integrates":[51],"text":[52],"generation,":[53],"forced":[54],"alignment,":[55],"speech":[56],"synthesis,":[57],"verification":[59],"via":[60],"ASR":[61],"technologies.":[62],"Our":[63,114],"method":[64],"has":[65],"synthesized":[66],"substantial":[68],"corpus":[69],"approximately":[71],"1200":[72],"hours":[73],"mixed":[76],"speech,":[77],"expanding":[79],"available":[81],"data.":[82],"Experiments":[83],"on":[84],"randomly":[86],"initialized":[87],"model":[88],"demonstrate":[89],"that":[90],"EMGL-generated":[92],"dataset":[93],"substantially":[94],"improves":[95],"accuracy.":[97],"improvement":[99],"achieved":[101],"without":[102],"need":[104,140],"for":[105],"additional":[106],"language":[107],"classifiers":[108],"or":[109],"refined":[110],"engineering":[112],"techniques.":[113],"results":[115],"highlight":[116],"transformative":[118],"potential":[119],"EMGL":[121],"addressing":[123],"persistent":[125],"challenge":[126],"scarcity":[129],"MECS-ASR,":[131],"offering":[132],"robust":[134],"solution":[135],"to":[136],"field":[138],"advancement.":[142]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}