{"id":"https://openalex.org/W4392903108","doi":"https://doi.org/10.1109/icassp48485.2024.10446258","title":"Attention-Guided Adaptation for Code-Switching Speech Recognition","display_name":"Attention-Guided Adaptation for Code-Switching Speech Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903108","doi":"https://doi.org/10.1109/icassp48485.2024.10446258"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5111148976","display_name":"Bobbi Aditya","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Bobbi Aditya","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Taiwan","Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043243811","display_name":"Mahdin Rohmatillah","orcid":"https://orcid.org/0000-0001-8417-2165"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Mahdin Rohmatillah","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Taiwan","Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063970123","display_name":"Liang-Hsuan Tai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148468","display_name":"Industrial Technology Research Institute","ror":"https://ror.org/05szzwt63","country_code":"TW","type":"nonprofit","lineage":["https://openalex.org/I4210148468"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Liang-Hsuan Tai","raw_affiliation_strings":["Industrial Technology Research Institute,Electronic and Optoelectronic System Research Labs,Taiwan","Electronic and Optoelectronic System Research Labs, Industrial Technology Research Institute, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Industrial Technology Research Institute,Electronic and Optoelectronic System Research Labs,Taiwan","institution_ids":["https://openalex.org/I4210148468"]},{"raw_affiliation_string":"Electronic and Optoelectronic System Research Labs, Industrial Technology Research Institute, Taiwan","institution_ids":["https://openalex.org/I4210148468"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Taiwan","Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6656,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.93565012,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10256","last_page":"10260"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9965999722480774,"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/code-switching","display_name":"Code-switching","score":0.869682788848877},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8446913361549377},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6244388818740845},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6200515627861023},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6157615780830383},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5470824837684631},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5046616792678833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49846506118774414},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.49480241537094116},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4486725330352783},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1693274974822998},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15527397394180298},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0804135799407959}],"concepts":[{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.869682788848877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8446913361549377},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6244388818740845},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6200515627861023},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6157615780830383},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5470824837684631},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5046616792678833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49846506118774414},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.49480241537094116},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4486725330352783},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1693274974822998},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15527397394180298},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0804135799407959},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W197277712","https://openalex.org/W202250699","https://openalex.org/W2014506068","https://openalex.org/W2926989360","https://openalex.org/W2962780374","https://openalex.org/W3097961301","https://openalex.org/W3106504817","https://openalex.org/W3138043709","https://openalex.org/W3160201895","https://openalex.org/W3198347216","https://openalex.org/W3198429080","https://openalex.org/W4220758154","https://openalex.org/W4224925597","https://openalex.org/W4225810142","https://openalex.org/W4296068966","https://openalex.org/W4297841820","https://openalex.org/W4323066695","https://openalex.org/W4378105483","https://openalex.org/W4385488739","https://openalex.org/W4385822470","https://openalex.org/W4385822890","https://openalex.org/W4388820551","https://openalex.org/W6759579507","https://openalex.org/W6790494085","https://openalex.org/W6847363464","https://openalex.org/W6850218400","https://openalex.org/W6852909395"],"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":{"The":[0,111],"prevalence":[1],"of":[2],"the":[3,13,25,45,61,114,121],"powerful":[4],"multilingual":[5,32],"models,":[6],"such":[7],"as":[8],"Whisper,":[9],"has":[10],"significantly":[11],"advanced":[12],"researches":[14],"on":[15,65,113],"speech":[16,33,117],"recognition.":[17,34],"However,":[18],"these":[19],"models":[20],"often":[21],"struggle":[22],"with":[23,107],"handling":[24],"code-switching":[26,116],"setting,":[27],"which":[28,93],"is":[29,75],"essential":[30],"in":[31,90],"Recent":[35],"studies":[36],"have":[37],"attempted":[38],"to":[39,50,77,103],"address":[40],"this":[41,69],"setting":[42],"by":[43],"separating":[44],"modules":[46],"for":[47,55,81],"different":[48],"languages":[49],"ensure":[51],"distinct":[52],"latent":[53],"representations":[54],"languages.":[56,110],"Some":[57],"other":[58],"methods":[59],"considered":[60],"switching":[62],"mechanism":[63],"based":[64],"language":[66,96],"identification.":[67],"In":[68],"study,":[70],"a":[71,91,125],"new":[72],"attention-guided":[73],"adaptation":[74],"proposed":[76,122],"conduct":[78],"parameter-efficient":[79],"learning":[80],"bilingual":[82],"ASR.":[83],"This":[84],"method":[85],"selects":[86],"those":[87,101],"attention":[88],"heads":[89,102],"model":[92],"closely":[94],"express":[95],"identities":[97],"and":[98],"then":[99],"guided":[100],"be":[104],"correctly":[105],"attended":[106],"their":[108],"corresponding":[109],"experiments":[112],"Mandarin-English":[115],"corpus":[118],"show":[119],"that":[120],"approach":[123],"achieves":[124],"14.2%":[126],"mixed":[127],"error":[128],"rate,":[129],"surpassing":[130],"state-of-the-art":[131],"method,":[132],"where":[133],"only":[134],"5.6%":[135],"additional":[136],"parameters":[137],"over":[138],"Whisper":[139],"are":[140],"trained.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}