{"id":"https://openalex.org/W7148426370","doi":"https://doi.org/10.1109/asru65441.2025.11434656","title":"AsyncSwitch: Asynchronous Text-Speech Adaptation for Code-Switched ASR","display_name":"AsyncSwitch: Asynchronous Text-Speech Adaptation for Code-Switched ASR","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148426370","doi":"https://doi.org/10.1109/asru65441.2025.11434656"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5017520459","display_name":"Tuan Minh Nguyen","orcid":"https://orcid.org/0000-0001-6408-8302"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Tuan Nguyen","raw_affiliation_strings":["Institute for Infocomm Research (I2R) A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R) A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132790689","display_name":"Huy-Dat Tran","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Huy-Dat Tran","raw_affiliation_strings":["Institute for Infocomm Research (I2R) A*STAR,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R) A*STAR,Singapore","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5017520459"],"corresponding_institution_ids":["https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87564489,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8224999904632568,"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":0.8224999904632568,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.09860000014305115,"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":0.010999999940395355,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.7146000266075134},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5917999744415283},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5609999895095825},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5073999762535095},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5055999755859375},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.5041000247001648},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.3375000059604645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8429999947547913},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7146000266075134},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6272000074386597},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5917999744415283},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5609999895095825},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5073999762535095},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5055999755859375},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.5041000247001648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43479999899864197},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30399999022483826},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.26100000739097595},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4085838794708252,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2884515606","https://openalex.org/W2936774411","https://openalex.org/W2973072704","https://openalex.org/W3096263335","https://openalex.org/W3096615836","https://openalex.org/W3152221657","https://openalex.org/W4385822500","https://openalex.org/W4386591026","https://openalex.org/W4391833135","https://openalex.org/W4392979802","https://openalex.org/W4406461879","https://openalex.org/W4415433892"],"related_works":[],"abstract_inverted_index":{"Developing":[0],"code-switched":[1,15,60,79],"ASR":[2,56],"systems":[3],"is":[4,21],"challenging":[5],"due":[6],"to":[7,13,38,54,58],"language":[8],"ambiguity":[9],"and":[10,36,75,84,92,118],"limited":[11,89],"exposure":[12],"multilingual,":[14],"data,":[16,91],"while":[17,111],"collecting":[18],"such":[19],"speech":[20],"costly.":[22],"Prior":[23],"work":[24],"generates":[25],"synthetic":[26],"audio":[27],"from":[28],"text,":[29,80],"but":[30],"these":[31],"methods":[32],"are":[33],"computationally":[34],"intensive":[35],"hard":[37],"scale.":[39],"We":[40],"introduce":[41],"AsyncSwitch,":[42],"a":[43,106],"novel":[44],"asynchronous":[45],"adaptation":[46],"framework":[47],"that":[48],"leverages":[49],"large-scale,":[50],"text-rich":[51],"web":[52],"data":[53],"pre-expose":[55],"models":[57],"diverse":[59],"domains":[61],"before":[62],"fine-tuning":[63],"on":[64,78,102],"paired":[65],"speech-text":[66,90],"corpora.":[67],"Our":[68],"three-stage":[69],"process":[70],"(1)":[71],"trains":[72],"decoder":[73,83],"self-attention":[74],"feedforward":[76],"layers":[77],"(2)":[81],"aligns":[82],"encoder":[85],"via":[86],"cross-attention":[87],"using":[88],"(3)":[93],"fully":[94],"fine-tunes":[95],"the":[96],"entire":[97],"model.":[98],"Experiments":[99],"with":[100],"Whisper":[101],"Malay-English":[103],"code-switching":[104],"demonstrate":[105],"9.02%":[107],"relative":[108],"WER":[109],"reduction,":[110],"improving":[112],"monolingual":[113],"performance":[114],"in":[115],"Singlish,":[116],"Malay,":[117],"other":[119],"English":[120],"variants.":[121]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}