{"id":"https://openalex.org/W4319862717","doi":"https://doi.org/10.1109/slt54892.2023.10023313","title":"Textual Data Augmentation for Arabic-English Code-Switching Speech Recognition","display_name":"Textual Data Augmentation for Arabic-English Code-Switching Speech Recognition","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862717","doi":"https://doi.org/10.1109/slt54892.2023.10023313"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023313","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5014592910","display_name":"Amir Hussein","orcid":"https://orcid.org/0000-0002-0820-4062"},"institutions":[{"id":"https://openalex.org/I4210152879","display_name":"Kantar Health (United States)","ror":"https://ror.org/04zbgcp34","country_code":"US","type":"company","lineage":["https://openalex.org/I4210152879"]},{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Amir Hussein","raw_affiliation_strings":["KANARI AI,California,USA","Johns Hopkins University, USA","KANARI AI, California, USA"],"affiliations":[{"raw_affiliation_string":"KANARI AI,California,USA","institution_ids":["https://openalex.org/I4210152879"]},{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"KANARI AI, California, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022279488","display_name":"Shammur Absar Chowdhury","orcid":"https://orcid.org/0000-0002-1331-2543"},"institutions":[{"id":"https://openalex.org/I4210087899","display_name":"Qatar Mining (Qatar)","ror":"https://ror.org/005r9px72","country_code":"QA","type":"company","lineage":["https://openalex.org/I4210087899"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Shammur Absar Chowdhury","raw_affiliation_strings":["Qatar Computing Research Institute,Qatar","Qatar Computing Research Institute, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute,Qatar","institution_ids":["https://openalex.org/I4210087899"]},{"raw_affiliation_string":"Qatar Computing Research Institute, Qatar","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047182137","display_name":"Ahmed Abdelal\u00ed","orcid":"https://orcid.org/0000-0002-4160-8181"},"institutions":[{"id":"https://openalex.org/I4210087899","display_name":"Qatar Mining (Qatar)","ror":"https://ror.org/005r9px72","country_code":"QA","type":"company","lineage":["https://openalex.org/I4210087899"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Ahmed Abdelali","raw_affiliation_strings":["Qatar Computing Research Institute,Qatar","Qatar Computing Research Institute, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute,Qatar","institution_ids":["https://openalex.org/I4210087899"]},{"raw_affiliation_string":"Qatar Computing Research Institute, Qatar","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Johns Hopkins University,USA","Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693435","display_name":"Ahmed Ali","orcid":"https://orcid.org/0000-0002-9186-7544"},"institutions":[{"id":"https://openalex.org/I4210087899","display_name":"Qatar Mining (Qatar)","ror":"https://ror.org/005r9px72","country_code":"QA","type":"company","lineage":["https://openalex.org/I4210087899"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Ahmed Ali","raw_affiliation_strings":["Qatar Computing Research Institute,Qatar","Qatar Computing Research Institute, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute,Qatar","institution_ids":["https://openalex.org/I4210087899"]},{"raw_affiliation_string":"Qatar Computing Research Institute, Qatar","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Johns Hopkins University,USA","Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5014592910"],"corresponding_institution_ids":["https://openalex.org/I145311948","https://openalex.org/I4210152879"],"apc_list":null,"apc_paid":null,"fwci":1.0173,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.74284227,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"777","last_page":"784"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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/T12031","display_name":"Speech and dialogue systems","score":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.8345044851303101},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.7783161401748657},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6905254125595093},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6488234400749207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5361338257789612},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.527208149433136},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.5191718339920044},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47231361269950867},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.46966588497161865},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.4393254220485687},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4202038645744324},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41753703355789185},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.19933480024337769},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11895176768302917},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08968806266784668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8345044851303101},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.7783161401748657},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6905254125595093},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6488234400749207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5361338257789612},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.527208149433136},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.5191718339920044},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47231361269950867},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.46966588497161865},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.4393254220485687},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4202038645744324},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41753703355789185},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.19933480024337769},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11895176768302917},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08968806266784668},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10023313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023313","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8500000238418579}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307764","display_name":"Microsoft","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1594833364","https://openalex.org/W1629199664","https://openalex.org/W1631260214","https://openalex.org/W1932968309","https://openalex.org/W1969754958","https://openalex.org/W2034585809","https://openalex.org/W2148708890","https://openalex.org/W2402146185","https://openalex.org/W2471147443","https://openalex.org/W2514741789","https://openalex.org/W2749874290","https://openalex.org/W2798348125","https://openalex.org/W2799473636","https://openalex.org/W2886744048","https://openalex.org/W2962780374","https://openalex.org/W2963077089","https://openalex.org/W2963212250","https://openalex.org/W2963499843","https://openalex.org/W2989143494","https://openalex.org/W2990897930","https://openalex.org/W3007095894","https://openalex.org/W3016108605","https://openalex.org/W3034724424","https://openalex.org/W3097972906","https://openalex.org/W3101648800","https://openalex.org/W3118036215","https://openalex.org/W3151027127","https://openalex.org/W3155609600","https://openalex.org/W3175210284","https://openalex.org/W3197295304","https://openalex.org/W3197472475","https://openalex.org/W3198544738","https://openalex.org/W4242105955","https://openalex.org/W4319862283","https://openalex.org/W6682026795","https://openalex.org/W6750226204","https://openalex.org/W6753759607"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2787311093","https://openalex.org/W2921174581","https://openalex.org/W2084531783","https://openalex.org/W2020757772"],"abstract_inverted_index":{"The":[0,36,129],"pervasiveness":[1],"of":[2,132,144],"intra-utterance":[3],"code-switching":[4],"(CS)":[5],"in":[6,113,119],"spoken":[7],"content":[8],"requires":[9],"that":[10,139],"speech":[11],"recognition":[12],"(ASR)":[13],"systems":[14],"handle":[15],"mixed":[16],"language.":[17],"Designing":[18],"a":[19,64,109],"CS-ASR":[20,69],"system":[21,48],"has":[22],"many":[23],"challenges,":[24],"mainly":[25],"due":[26],"to":[27,44,97],"data":[28,74],"scarcity,":[29],"grammatical":[30],"structure":[31],"complexity,":[32],"and":[33,88,100,117],"domain":[34],"mismatch.":[35],"most":[37],"common":[38],"method":[39],"for":[40,68],"addressing":[41],"CS":[42,53,78,103,126],"is":[43,143],"train":[45],"an":[46],"ASR":[47,120],"with":[49,56,75],"the":[50,72,133],"available":[51],"transcribed":[52],"speech,":[54],"along":[55],"monolingual":[57,73],"data.":[58],"In":[59],"this":[60],"work,":[61],"we":[62],"propose":[63],"zero-shot":[65],"learning":[66],"methodology":[67],"by":[70],"augmenting":[71],"artificially":[76],"generating":[77],"text.":[79],"We":[80],"based":[81],"our":[82],"approach":[83],"on":[84,122],"random":[85,99],"lexical":[86],"replacements":[87],"Equivalence":[89],"Constraint":[90],"(EC)":[91],"while":[92],"exploiting":[93],"aligned":[94],"translation":[95],"pairs":[96],"generate":[98],"grammatically":[101],"valid":[102,125],"content.":[104],"Our":[105],"empirical":[106],"results":[107],"show":[108],"65.5%":[110],"relative":[111],"reduction":[112],"language":[114],"model":[115],"perplexity,":[116],"7.7%":[118],"WER":[121],"two":[123],"ecologically":[124],"test":[127],"sets.":[128],"human":[130],"evaluation":[131],"generated":[134],"text":[135],"using":[136],"EC":[137],"suggests":[138],"more":[140],"than":[141],"80%":[142],"adequate":[145],"quality.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}