{"id":"https://openalex.org/W4416037679","doi":"https://doi.org/10.18653/v1/2025.arabicnlp-main.22","title":"TEDxTN: A Three-way Speech Translation Corpus for Code-Switched Tunisian Arabic - English","display_name":"TEDxTN: A Three-way Speech Translation Corpus for Code-Switched Tunisian Arabic - English","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416037679","doi":"https://doi.org/10.18653/v1/2025.arabicnlp-main.22"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.arabicnlp-main.22","doi":"https://doi.org/10.18653/v1/2025.arabicnlp-main.22","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-main.22","pdf_url":"https://aclanthology.org/2025.arabicnlp-main.22.pdf","source":{"id":"https://openalex.org/S7407085968","display_name":"Arabic Natural Language Processing Workshop (WANLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Third Arabic Natural Language Processing Conference","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2025.arabicnlp-main.22.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079465565","display_name":"Fethi Bougares","orcid":"https://orcid.org/0000-0002-6494-2350","observed_orcids":["https://orcid.org/0000-0002-6494-2350"]},"institutions":[{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fethi Bougares","raw_affiliation_strings":["ELYADATA , Paris , France,","Laboratoire Informatique d'Avignon , Avignon , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ELYADATA , Paris , France,","institution_ids":[]},{"raw_affiliation_string":"Laboratoire Informatique d'Avignon , Avignon , France","institution_ids":["https://openalex.org/I4210119991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056172842","display_name":"Salima Mdhaffar","orcid":"https://orcid.org/0000-0002-8472-6890","observed_orcids":["https://orcid.org/0000-0002-8472-6890"]},"institutions":[{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Salima Mdhaffar","raw_affiliation_strings":["Laboratoire Informatique d'Avignon , Avignon , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire Informatique d'Avignon , Avignon , France","institution_ids":["https://openalex.org/I4210119991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092596246","display_name":"Haroun Elleuch","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Haroun Elleuch","raw_affiliation_strings":["ELYADATA , Paris , France,","Laboratoire Informatique d'Avignon , Avignon , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ELYADATA , Paris , France,","institution_ids":[]},{"raw_affiliation_string":"Laboratoire Informatique d'Avignon , Avignon , France","institution_ids":["https://openalex.org/I4210119991"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081852717","display_name":"Yannick Est\u00e8ve","orcid":"https://orcid.org/0000-0002-3656-8883","observed_orcids":["https://orcid.org/0000-0002-3656-8883"]},"institutions":[{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yannick Est\u00e8ve","raw_affiliation_strings":["Laboratoire Informatique d'Avignon , Avignon , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratoire Informatique d'Avignon , Avignon , France","institution_ids":["https://openalex.org/I4210119991"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210119991"],"apc_list":null,"apc_paid":null,"fwci":0.9533,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77305331,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"278","last_page":"287"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9926999807357788,"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":0.9926999807357788,"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":0.004800000227987766,"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":0.0008999999845400453,"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/tunisian-arabic","display_name":"Tunisian Arabic","score":0.9369999766349792},{"id":"https://openalex.org/keywords/code-switching","display_name":"code-switching","score":0.7960000038146973},{"id":"https://openalex.org/keywords/speech-translation","display_name":"speech translation","score":0.9110000133514404},{"id":"https://openalex.org/keywords/tedx-talks","display_name":"TEDx talks","score":0.6949999928474426},{"id":"https://openalex.org/keywords/arabic-dialects","display_name":"Arabic dialects","score":0.652999997138977},{"id":"https://openalex.org/keywords/data-scarcity","display_name":"data scarcity","score":0.6200000047683716},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"speech segmentation","score":0.5350000262260437},{"id":"https://openalex.org/keywords/speech-transcription","display_name":"speech transcription","score":0.7409999966621399},{"id":"https://openalex.org/keywords/annotation-guidelines","display_name":"annotation guidelines","score":0.753000020980835},{"id":"https://openalex.org/keywords/end-to-end-speech-translation","display_name":"end-to-end speech translation","score":0.7519999742507935},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.7870000004768372}],"concepts":[{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.6546000242233276},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4945000112056732},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47780001163482666},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.44909998774528503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44679999351501465},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.36890000104904175},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.33889999985694885},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33649998903274536},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.31470000743865967},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.2840000092983246},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.arabicnlp-main.22","doi":"https://doi.org/10.18653/v1/2025.arabicnlp-main.22","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-main.22","pdf_url":"https://aclanthology.org/2025.arabicnlp-main.22.pdf","source":{"id":"https://openalex.org/S7407085968","display_name":"Arabic Natural Language Processing Workshop (WANLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Third Arabic Natural Language Processing Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.10780","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.10780","pdf_url":"https://arxiv.org/pdf/2511.10780","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.10780","doi":"https://doi.org/10.48550/arxiv.2511.10780","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.10780","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.arabicnlp-main.22","doi":"https://doi.org/10.18653/v1/2025.arabicnlp-main.22","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.arabicnlp-main.22","pdf_url":"https://aclanthology.org/2025.arabicnlp-main.22.pdf","source":{"id":"https://openalex.org/S7407085968","display_name":"Arabic Natural Language Processing Workshop (WANLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Third Arabic Natural Language Processing Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1454328438","display_name":"Exchanges for SPEech ReseArch aNd TechnOlogies","funder_award_id":"101007666","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320326256","display_name":"Grand \u00c9quipement National De Calcul Intensif","ror":"https://ror.org/0010d1q40"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416037679.pdf","grobid_xml":"https://content.openalex.org/works/W4416037679.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416037648","https://openalex.org/W4309870515","https://openalex.org/W7118181729","https://openalex.org/W2250862217","https://openalex.org/W6944068083","https://openalex.org/W4403322716","https://openalex.org/W7131843530","https://openalex.org/W4392932033","https://openalex.org/W4410313687","https://openalex.org/W2805530518"],"abstract_inverted_index":{"In":[0],"this":[1,132],"paper,":[2],"we":[3],"introduce":[4],"TEDxTN,":[5],"the":[6,22,27,74,83,116,145],"first":[7,117],"publicly":[8,79,121],"available":[9,122],"Tunisian":[10,128,150],"Arabic":[11,35],"to":[12,25,87],"English":[13],"speech":[14,57,123],"translation":[15,124],"dataset.This":[16],"work":[17],"is":[18,115,133],"in":[19],"line":[20],"with":[21,58,63],"ongoing":[23],"effort":[24],"mitigate":[26],"data":[28],"scarcity":[29],"obstacle":[30],"for":[31,97],"a":[32,134],"number":[33],"of":[34,56,71,85,101,126,149],"dialects.We":[36],"collected,":[37],"segmented,":[38],"transcribed":[39],"and":[40,77,104,110,120,140],"translated":[41],"108":[42],"TEDx":[43],"talks":[44,52,89],"following":[45],"our":[46],"internally":[47],"developed":[48],"annotations":[49],"guidelines.The":[50],"collected":[51],"represent":[53],"25":[54],"hours":[55],"code-switching":[59],"that":[60,131,137],"cover":[61],"speakers":[62],"various":[64],"accents":[65],"from":[66],"over":[67],"11":[68],"different":[69],"regions":[70],"Tunisia.We":[72],"make":[73],"annotation":[75],"guidelines":[76],"corpus":[78,114,125],"available.This":[80],"will":[81],"enable":[82],"extension":[84],"TEDxTN":[86],"new":[88],"as":[90],"they":[91],"become":[92],"available.We":[93],"also":[94],"report":[95],"results":[96],"strong":[98],"baseline":[99],"systems":[100],"Speech":[102,105],"Recognition":[103],"Translation":[106],"using":[107],"multiple":[108],"pre-trained":[109],"fine-tuned":[111],"end-to-end":[112],"models.This":[113],"open":[118],"source":[119],"Code-Switching":[127],"dialect.We":[129],"believe":[130],"valuable":[135],"resource":[136],"can":[138],"motivate":[139],"facilitate":[141],"further":[142],"research":[143],"on":[144],"natural":[146],"language":[147],"processing":[148],"Dialect.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2025-11-08T00:00:00"}
