{"id":"https://openalex.org/W4416771680","doi":"https://doi.org/10.1109/sped67700.2025.11252407","title":"Cross-lingual Transfer Learning Experiments for Arabic ASR","display_name":"Cross-lingual Transfer Learning Experiments for Arabic ASR","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416771680","doi":"https://doi.org/10.1109/sped67700.2025.11252407"},"language":null,"primary_location":{"id":"doi:10.1109/sped67700.2025.11252407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped67700.2025.11252407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","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/A5116341275","display_name":"Amin Hassairi","orcid":null},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Amin Hassairi","raw_affiliation_strings":["Budapest University of Technology and Economics,Dept. of Telecommunications and Artificial Intelligence,Budapest,Hungary"],"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics,Dept. of Telecommunications and Artificial Intelligence,Budapest,Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020514527","display_name":"P\u00e9ter Mihajlik","orcid":"https://orcid.org/0000-0001-7532-9773"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"P\u00e9ter Mihajlik","raw_affiliation_strings":["Budapest University of Technology and Economics,Dept. of Telecommunications and Artificial Intelligence,Budapest,Hungary"],"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics,Dept. of Telecommunications and Artificial Intelligence,Budapest,Hungary","institution_ids":["https://openalex.org/I29770179"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5116341275"],"corresponding_institution_ids":["https://openalex.org/I29770179"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20611741,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"108","last_page":"113"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7659000158309937,"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":0.7659000158309937,"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":0.03849999979138374,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.013799999840557575,"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/transfer-of-learning","display_name":"Transfer of learning","score":0.7077999711036682},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5792999863624573},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5681999921798706},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.5400000214576721},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.536300003528595},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5314000248908997},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4982999861240387},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.49459999799728394},{"id":"https://openalex.org/keywords/transfer-of-training","display_name":"Transfer of training","score":0.48539999127388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7968000173568726},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.7077999711036682},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6614999771118164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6570000052452087},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5792999863624573},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5681999921798706},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5400000214576721},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.536300003528595},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5314000248908997},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4982999861240387},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.49459999799728394},{"id":"https://openalex.org/C2777938197","wikidata":"https://www.wikidata.org/wiki/Q7834022","display_name":"Transfer of training","level":2,"score":0.48539999127388},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46889999508857727},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.40119999647140503},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.34790000319480896},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.32120001316070557},{"id":"https://openalex.org/C2779178101","wikidata":"https://www.wikidata.org/wiki/Q6987274","display_name":"Negative transfer","level":3,"score":0.31119999289512634},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C132165367","wikidata":"https://www.wikidata.org/wiki/Q34049","display_name":"Semitic languages","level":3,"score":0.27889999747276306},{"id":"https://openalex.org/C134121241","wikidata":"https://www.wikidata.org/wiki/Q899301","display_name":"Yield (engineering)","level":2,"score":0.26969999074935913}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sped67700.2025.11252407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped67700.2025.11252407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1970890968","https://openalex.org/W2091746061","https://openalex.org/W2127141656","https://openalex.org/W2160815625","https://openalex.org/W2327501763","https://openalex.org/W2586568968","https://openalex.org/W2766219058","https://openalex.org/W2963303951","https://openalex.org/W3194921972","https://openalex.org/W3198429080","https://openalex.org/W3209059054","https://openalex.org/W4285144981","https://openalex.org/W4297798704","https://openalex.org/W4388692863"],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"Speech":[1],"Recognition":[2],"(ASR)":[3],"for":[4,150,160],"low-resource":[5,161],"languages":[6],"such":[7],"as":[8],"Arabic":[9,30,39,101,151],"remains":[10],"a":[11,64],"challenging":[12],"task":[13],"due":[14],"to":[15,124,143],"the":[16,27,34,75,131,144,155],"scarcity":[17],"of":[18,29,66,133,146,157],"annotated":[19],"data":[20],"and":[21,46,61,70,120,127,153],"linguistic":[22],"diversity.":[23],"This":[24,140],"paper":[25],"explores":[26],"development":[28],"ASR":[31,152],"models":[32,43,54,81,111],"using":[33,51],"Mozilla":[35],"Common":[36],"Voice":[37],"11.0":[38],"dataset.":[40],"We":[41],"train":[42],"from":[44,78,84],"scratch":[45],"investigate":[47],"cross-lingual":[48,138],"transfer":[49,90,148],"learning":[50,91],"pretrained":[52,80,115],"Conformer":[53],"trained":[55],"on":[56],"high-resource":[57],"languages,":[58],"specifically":[59],"English":[60,114],"French.":[62],"Through":[63],"series":[65],"experiments":[67],"involving":[68],"language":[69,135,162],"domain":[71],"adaptation,":[72],"we":[73],"evaluate":[74],"performance":[76],"gains":[77],"leveraging":[79],"versus":[82],"training":[83,102],"scratch.":[85],"Our":[86],"findings":[87],"demonstrate":[88],"that":[89,110],"significantly":[92],"improves":[93],"model":[94],"performance,":[95],"especially":[96],"in":[97,137],"scenarios":[98],"with":[99,113],"limited":[100],"data.":[103],"Word":[104],"Error":[105],"Rate":[106],"(WER)":[107],"comparisons":[108],"reveal":[109],"initialized":[112],"weights":[116],"yield":[117],"better":[118],"generalization":[119],"lower":[121],"WERs":[122],"compared":[123],"both":[125],"scratch-trained":[126],"French-initialized":[128],"models,":[129],"highlighting":[130],"importance":[132],"source":[134],"selection":[136],"ASR.":[139],"work":[141],"contributes":[142],"understanding":[145],"efficient":[147],"strategies":[149],"underscores":[154],"potential":[156],"multilingual":[158],"pretraining":[159],"modeling.":[163]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-27T00:00:00"}