{"id":"https://openalex.org/W4392932033","doi":"https://doi.org/10.1109/icassp48485.2024.10445734","title":"Leveraging Data Collection and Unsupervised Learning for Code-Switched Tunisian Arabic Automatic Speech Recognition","display_name":"Leveraging Data Collection and Unsupervised Learning for Code-Switched Tunisian Arabic Automatic Speech Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392932033","doi":"https://doi.org/10.1109/icassp48485.2024.10445734"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445734","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/A5100576683","display_name":"Ahmed Abdallah","orcid":null},"institutions":[{"id":"https://openalex.org/I3131031036","display_name":"Mediterranean School of Business","ror":"https://ror.org/02fyv5292","country_code":"TN","type":"education","lineage":["https://openalex.org/I3131031036"]}],"countries":["TN"],"is_corresponding":true,"raw_author_name":"Ahmed Amine Ben Abdallah","raw_affiliation_strings":["Tunis Business School"],"affiliations":[{"raw_affiliation_string":"Tunis Business School","institution_ids":["https://openalex.org/I3131031036"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092919145","display_name":"Ata Kabboudi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130704","display_name":"University of Michigan\u2013Dearborn","ror":"https://ror.org/035wtm547","country_code":"US","type":"education","lineage":["https://openalex.org/I4210130704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ata Kabboudi","raw_affiliation_strings":["University of Michigan-Dearborn"],"affiliations":[{"raw_affiliation_string":"University of Michigan-Dearborn","institution_ids":["https://openalex.org/I4210130704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092919146","display_name":"Amir Kanoun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amir Kanoun","raw_affiliation_strings":["Abshore"],"affiliations":[{"raw_affiliation_string":"Abshore","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040954517","display_name":"Salah Zaiem","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I4210145102","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Salah Zaiem","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com Paris"],"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com Paris","institution_ids":["https://openalex.org/I4210165912"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100576683"],"corresponding_institution_ids":["https://openalex.org/I3131031036"],"apc_list":null,"apc_paid":null,"fwci":2.5383,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90149646,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"12607","last_page":"12611"},"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":0.9987999796867371,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"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/spelling","display_name":"Spelling","score":0.7995325326919556},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7871139645576477},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5527973771095276},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5129706263542175},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.47711995244026184},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.47157731652259827},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.45064669847488403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4319550395011902},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.35752788186073303}],"concepts":[{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.7995325326919556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7871139645576477},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5527973771095276},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5129706263542175},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.47711995244026184},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47157731652259827},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.45064669847488403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4319550395011902},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.35752788186073303},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/icassp48485.2024.10445734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445734","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":[{"id":"https://openalex.org/F4320326256","display_name":"Grand \u00c9quipement National De Calcul Intensif","ror":"https://ror.org/0010d1q40"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1976805110","https://openalex.org/W2143612262","https://openalex.org/W2591804103","https://openalex.org/W2749874290","https://openalex.org/W2760231680","https://openalex.org/W2906725291","https://openalex.org/W3030437843","https://openalex.org/W3037465386","https://openalex.org/W3042170933","https://openalex.org/W3185689807","https://openalex.org/W3197472475","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4243213367","https://openalex.org/W4288408927","https://openalex.org/W4311000453","https://openalex.org/W4372269995","https://openalex.org/W4378105483","https://openalex.org/W4385822952","https://openalex.org/W6679855610","https://openalex.org/W6691505291","https://openalex.org/W6770434673","https://openalex.org/W6780815891","https://openalex.org/W6845587207","https://openalex.org/W6852909395"],"related_works":["https://openalex.org/W2100947578","https://openalex.org/W2161008081","https://openalex.org/W1555832326","https://openalex.org/W4298186509","https://openalex.org/W2556702969","https://openalex.org/W217221262","https://openalex.org/W611030372","https://openalex.org/W1974418053","https://openalex.org/W2081317458","https://openalex.org/W2021532426"],"abstract_inverted_index":{"Crafting":[0],"an":[1],"effective":[2],"Automatic":[3],"Speech":[4],"Recognition":[5],"(ASR)":[6],"solution":[7],"for":[8,136],"dialects":[9],"demands":[10],"innovative":[11],"approaches":[12,63],"that":[13],"not":[14],"only":[15],"address":[16,33],"the":[17,24,34,40,66,83,98,127],"data":[18,47,128],"scarcity":[19],"issue":[20],"but":[21],"also":[22],"navigate":[23],"intricacies":[25],"of":[26,85,93],"linguistic":[27,76,117],"diversity.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32,56,88],"aforementioned":[35],"ASR":[36],"challenge,":[37],"focusing":[38],"on":[39,68],"Tunisian":[41,70,120],"dialect.":[42],"First,":[43],"textual":[44],"and":[45,50,60,77,81,123,125,132,139],"audio":[46,113],"is":[48],"collected":[49],"in":[51,104,115],"some":[52],"cases":[53],"annotated.":[54],"Second,":[55],"explore":[57],"self-supervision,":[58],"semi-supervision":[59],"few-shot":[61],"code-switching":[62],"to":[64,96,111],"push":[65],"state-of-the-art":[67],"different":[69,74],"test":[71],"sets;":[72],"covering":[73],"acoustic,":[75],"prosodic":[78],"conditions.":[79],"Finally,":[80],"given":[82],"absence":[84],"conventional":[86],"spelling,":[87],"produce":[89],"a":[90,116],"human":[91],"evaluation":[92],"our":[94,105],"transcripts":[95],"avoid":[97],"noise":[99],"coming":[100],"from":[101],"spelling":[102],"inadequacies":[103],"testing":[106,133],"references.":[107],"Our":[108],"models,":[109],"allowing":[110],"transcribe":[112],"samples":[114],"mix":[118],"involving":[119],"Arabic,":[121],"English":[122],"French,":[124],"all":[126],"used":[129],"during":[130],"training":[131],"are":[134],"released":[135],"public":[137],"use":[138],"further":[140],"improvements.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
