{"id":"https://openalex.org/W7118181729","doi":"https://doi.org/10.1109/aiccsa66935.2025.11315311","title":"Automatic Code-switched Academic Tunisian Arabic Speech Recognition","display_name":"Automatic Code-switched Academic Tunisian Arabic Speech Recognition","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7118181729","doi":"https://doi.org/10.1109/aiccsa66935.2025.11315311"},"language":null,"primary_location":{"id":"doi:10.1109/aiccsa66935.2025.11315311","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa66935.2025.11315311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACS 22nd International Conference on Computer Systems and Applications (AICCSA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5064042172","display_name":"Fatma Zahra Besdouri","orcid":"https://orcid.org/0009-0004-0985-3955"},"institutions":[{"id":"https://openalex.org/I142899784","display_name":"University of Sfax","ror":"https://ror.org/04d4sd432","country_code":"TN","type":"education","lineage":["https://openalex.org/I142899784"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Fatma Zahra Besdouri","raw_affiliation_strings":["MIRACL Lab University of Sfax,ANLP Research Group,Sfax,Tunisia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIRACL Lab University of Sfax,ANLP Research Group,Sfax,Tunisia","institution_ids":["https://openalex.org/I142899784"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121972136","display_name":"In\u00e8s Zribi","orcid":null},"institutions":[{"id":"https://openalex.org/I142899784","display_name":"University of Sfax","ror":"https://ror.org/04d4sd432","country_code":"TN","type":"education","lineage":["https://openalex.org/I142899784"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"In\u00e8s Zribi","raw_affiliation_strings":["MIRACL Lab University of Sfax,ANLP Research Group,Sfax,Tunisia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIRACL Lab University of Sfax,ANLP Research Group,Sfax,Tunisia","institution_ids":["https://openalex.org/I142899784"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102717363","display_name":"Lamia Hadrich Belguith","orcid":"https://orcid.org/0000-0002-5063-9246"},"institutions":[{"id":"https://openalex.org/I142899784","display_name":"University of Sfax","ror":"https://ror.org/04d4sd432","country_code":"TN","type":"education","lineage":["https://openalex.org/I142899784"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Lamia Hadrich Belguith","raw_affiliation_strings":["MIRACL Lab University of Sfax,ANLP Research Group,Sfax,Tunisia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIRACL Lab University of Sfax,ANLP Research Group,Sfax,Tunisia","institution_ids":["https://openalex.org/I142899784"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I142899784"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7775999903678894,"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":0.7775999903678894,"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":0.08410000056028366,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.03200000151991844,"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/lexicon","display_name":"Lexicon","score":0.6349999904632568},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6100999712944031},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.5950000286102295},{"id":"https://openalex.org/keywords/phonetic-transcription","display_name":"Phonetic transcription","score":0.41940000653266907},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.3889000117778778},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.38519999384880066},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.37049999833106995},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3361000120639801}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7603999972343445},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6621000170707703},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6442999839782715},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.6349999904632568},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6100999712944031},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5950000286102295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4984999895095825},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.41940000653266907},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.3889000117778778},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37049999833106995},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3361000120639801},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.2978000044822693},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.295199990272522},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26759999990463257},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.2619999945163727},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aiccsa66935.2025.11315311","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa66935.2025.11315311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACS 22nd International Conference on Computer Systems and Applications (AICCSA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4221648871898651,"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":21,"referenced_works":["https://openalex.org/W2164777277","https://openalex.org/W2749874290","https://openalex.org/W3147984406","https://openalex.org/W3185689807","https://openalex.org/W3197295304","https://openalex.org/W3197472475","https://openalex.org/W3213029956","https://openalex.org/W4210250275","https://openalex.org/W4285158119","https://openalex.org/W4312712916","https://openalex.org/W4385573226","https://openalex.org/W4392932033","https://openalex.org/W4400029993","https://openalex.org/W4401236403","https://openalex.org/W4402671401","https://openalex.org/W4404738457","https://openalex.org/W4405545612","https://openalex.org/W4407575444","https://openalex.org/W4407876512","https://openalex.org/W4408062379","https://openalex.org/W4408984945"],"related_works":[],"abstract_inverted_index":{"Aiming":[0],"to":[1,45,52,110],"support":[2],"researchers":[3],"by":[4,34],"answering":[5],"their":[6],"questions,":[7],"this":[8,53],"paper":[9],"presents":[10],"the":[11,27,67,127],"first":[12],"module":[13],"of":[14,38,62],"a":[15,35,47],"virtual":[16],"assistant":[17],"for":[18],"Tunisian":[19],"Arabic":[20],"(TA):":[21],"Automatic":[22],"Speech":[23],"Recognition":[24],"(ASR).":[25],"Given":[26],"specialized":[28],"lexicon":[29],"used,":[30],"which":[31],"is":[32,44],"characterized":[33],"high":[36],"rate":[37],"Code-Switching":[39],"(CS),":[40],"our":[41,74,90],"primary":[42],"objective":[43],"create":[46],"new":[48],"dataset,":[49],"Tunacad,":[50],"tailored":[51],"context.":[54],"Tunacad":[55],"comprises":[56],"$\\mathbf{1":[57],"2.":[58],"5":[59],"6}$":[60],"hours":[61],"CS":[63,76,121],"spontaneous":[64],"speech":[65],"in":[66,130],"academic":[68],"domain.":[69],"Additionally,":[70,105],"we":[71,92,106,125],"experiment":[72],"with":[73],"proposed":[75],"corpus":[77],"on":[78,89],"predefined":[79],"ASR":[80,87],"models,":[81],"Whisper":[82],"and":[83,102,120],"Wav2vec2-XLR-S.":[84],"To":[85],"enhance":[86],"performance":[88],"corpus,":[91],"apply":[93],"several":[94],"techniques,":[95],"such":[96],"as":[97],"automatic":[98],"orthographic":[99],"correction,":[100],"normalization,":[101],"prompt-based":[103],"correction.":[104],"incorporate":[107],"human":[108],"evaluation":[109],"assess":[111],"transcription":[112],"quality":[113],"beyond":[114],"surface-level":[115],"accuracy.":[116],"Through":[117],"these":[118],"experiments":[119],"errors":[122],"analysis":[123],"statistics,":[124],"highlight":[126],"persistent":[128],"challenges":[129],"processing":[131],"TA":[132],"speech.":[133]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-05T00:00:00"}