{"id":"https://openalex.org/W4416799930","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248981","title":"Language Awareness in Code-Switching Speech Recognition","display_name":"Language Awareness in Code-Switching Speech Recognition","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799930","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11248981"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11248981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/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":true,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Hsinchu,Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","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":["Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Hsinchu,Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5061908942"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20742641,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1086","last_page":"1091"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7904000282287598,"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":0.7904000282287598,"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":0.03869999945163727,"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":0.037700001150369644,"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/cued-speech","display_name":"Cued speech","score":0.5917999744415283},{"id":"https://openalex.org/keywords/speech-error","display_name":"Speech error","score":0.5849000215530396},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4196999967098236},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.3903000056743622},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.38989999890327454},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3898000121116638},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.37070000171661377},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3504999876022339}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.743399977684021},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6243000030517578},{"id":"https://openalex.org/C83195618","wikidata":"https://www.wikidata.org/wiki/Q590951","display_name":"Cued speech","level":2,"score":0.5917999744415283},{"id":"https://openalex.org/C541956065","wikidata":"https://www.wikidata.org/wiki/Q2250680","display_name":"Speech error","level":3,"score":0.5849000215530396},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46160000562667847},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4196999967098236},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.38989999890327454},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3898000121116638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.383899986743927},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.37070000171661377},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.27790001034736633},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2702000141143799},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.259799987077713},{"id":"https://openalex.org/C2780035574","wikidata":"https://www.wikidata.org/wiki/Q30081","display_name":"Multilingualism","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.25529998540878296},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11248981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11248981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":27,"referenced_works":["https://openalex.org/W197277712","https://openalex.org/W2926989360","https://openalex.org/W2962780374","https://openalex.org/W3097961301","https://openalex.org/W3138043709","https://openalex.org/W3160201895","https://openalex.org/W3163201210","https://openalex.org/W3198429080","https://openalex.org/W3208178363","https://openalex.org/W4220758154","https://openalex.org/W4297841499","https://openalex.org/W4297841565","https://openalex.org/W4297841820","https://openalex.org/W4313887415","https://openalex.org/W4372259817","https://openalex.org/W4375869049","https://openalex.org/W4385822890","https://openalex.org/W4388820551","https://openalex.org/W4389518325","https://openalex.org/W4391021740","https://openalex.org/W4392902746","https://openalex.org/W4392903108","https://openalex.org/W4400905918","https://openalex.org/W4405634116","https://openalex.org/W4406858895","https://openalex.org/W4415524006","https://openalex.org/W4415797743"],"related_works":[],"abstract_inverted_index":{"Code-switching":[0],"speech":[1,21,28,35,52,62,113],"is":[2,17,29,78,85],"observed":[3],"when":[4],"two":[5],"or":[6],"more":[7],"languages":[8],"are":[9,63],"spoken":[10],"in":[11,19,49,59,75],"a":[12,33,81,88],"single":[13],"utterance.":[14],"This":[15,72],"phenomenon":[16],"common":[18],"multilingual":[20,41],"applications.":[22],"The":[23,108],"ability":[24],"to":[25,31,66,91,94],"recognize":[26],"code-switching":[27,61,112],"essential":[30],"develop":[32],"bilingual":[34],"recognition":[36],"system.":[37],"While":[38],"the":[39,56,67,124,143],"pre-trained":[40],"model":[42],"such":[43],"as":[44],"Whisper":[45,93],"has":[46],"shown":[47],"promising":[48],"recognizing":[50],"monolingual":[51],"from":[53],"different":[54],"languages,":[55],"previous":[57],"works":[58],"handling":[60],"suboptimal":[64],"due":[65],"language":[68,98,106],"mixing":[69],"and":[70,117,139],"inaccuracy.":[71],"circumstance,":[73],"existing":[74],"attention":[76],"maps,":[77],"tackled":[79],"through":[80,87],"new":[82],"strategy,":[83],"which":[84],"fulfilled":[86],"two-stage":[89],"optimization":[90],"ensure":[92],"be":[95],"aware":[96],"of":[97,99,128],"each":[100],"word":[101],"by":[102],"attending":[103],"its":[104],"correct":[105],"identity.":[107],"experiments":[109],"on":[110],"Mandarin-English":[111],"using":[114],"SEAME,":[115],"ASCEND":[116],"NTUT":[118],"show":[119],"that":[120],"this":[121],"method":[122],"achieves":[123],"mixed":[125],"error":[126],"rates":[127],"<tex":[129],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[130],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\text{1":[131],"3.":[132],"8":[133],"\\%},":[134],"\\text{2":[135],"6.":[136],"7":[137],"\\%}$</tex>":[138],"11.8":[140],"%,":[141],"surpassing":[142],"other":[144],"methods,":[145],"respectively,":[146],"with":[147],"very":[148],"few":[149],"additional":[150],"adapter":[151],"parameters.":[152]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}
