{"id":"https://openalex.org/W7166576532","doi":"https://doi.org/10.63317/4wy5qhn7npqa","title":"Inverse Text Normalization for Arabic Numbers in Streaming ASR","display_name":"Inverse Text Normalization for Arabic Numbers in Streaming ASR","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7166576532","doi":"https://doi.org/10.63317/4wy5qhn7npqa"},"language":"en","primary_location":{"id":"doi:10.63317/4wy5qhn7npqa","doi":"https://doi.org/10.63317/4wy5qhn7npqa","is_oa":true,"landing_page_url":"https://doi.org/10.63317/4wy5qhn7npqa","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/cawl/pdf/2026.cawl-1.11.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/cawl/pdf/2026.cawl-1.11.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116594514","display_name":"Enas Albasiri","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Enas Albasiri","raw_affiliation_strings":["NVIDIA Santa Clara , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Santa Clara , CA , USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139553699","display_name":"Myungjong Kim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Myungjong Kim","raw_affiliation_strings":["NVIDIA Santa Clara , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Santa Clara , CA , USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034496926","display_name":"Nourchene Ferchichi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nourchene Ferchichi","raw_affiliation_strings":["NVIDIA Santa Clara , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Santa Clara , CA , USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124283176","display_name":"Oluwatobi Olabiyi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oluwatobi Olabiyi","raw_affiliation_strings":["NVIDIA Santa Clara , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Santa Clara , CA , USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42742676,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"101","last_page":"106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":9.999999747378752e-05,"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/T12031","display_name":"Speech and dialogue systems","score":0.0,"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/streaming-speech-recognition","display_name":"streaming speech recognition","score":0.9269999861717224},{"id":"https://openalex.org/keywords/arabic-dialects","display_name":"Arabic dialects","score":0.7070000171661377},{"id":"https://openalex.org/keywords/gender-polarity","display_name":"gender polarity","score":0.4880000054836273},{"id":"https://openalex.org/keywords/diacritization","display_name":"diacritization","score":0.8309999704360962},{"id":"https://openalex.org/keywords/orthographic-variation","display_name":"orthographic variation","score":0.7649999856948853},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.703000009059906},{"id":"https://openalex.org/keywords/classical-arabic","display_name":"Classical Arabic","score":0.9900000095367432}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7767999768257141},{"id":"https://openalex.org/C204160518","wikidata":"https://www.wikidata.org/wiki/Q122653","display_name":"Numeral system","level":2,"score":0.7646999955177307},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6254000067710876},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.604200005531311},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5945000052452087},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5494999885559082},{"id":"https://openalex.org/C82054205","wikidata":"https://www.wikidata.org/wiki/Q29961325","display_name":"Arabic numerals","level":2,"score":0.5220000147819519},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48500001430511475},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.46860000491142273},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.45910000801086426},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4212999939918518},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.42010000348091125},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.398499995470047},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.39559999108314514},{"id":"https://openalex.org/C41417386","wikidata":"https://www.wikidata.org/wiki/Q147276","display_name":"Proper noun","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C2778364766","wikidata":"https://www.wikidata.org/wiki/Q36510","display_name":"Modern Greek","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.63317/4wy5qhn7npqa","doi":"https://doi.org/10.63317/4wy5qhn7npqa","is_oa":true,"landing_page_url":"https://doi.org/10.63317/4wy5qhn7npqa","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/cawl/pdf/2026.cawl-1.11.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.63317/4wy5qhn7npqa","doi":"https://doi.org/10.63317/4wy5qhn7npqa","is_oa":true,"landing_page_url":"https://doi.org/10.63317/4wy5qhn7npqa","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/cawl/pdf/2026.cawl-1.11.pdf","source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.7752842307090759}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166576532.pdf","grobid_xml":"https://content.openalex.org/works/W7166576532.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6999387737","https://openalex.org/W4415433256","https://openalex.org/W7222013684","https://openalex.org/W7213953058","https://openalex.org/W4319862420","https://openalex.org/W3087250107","https://openalex.org/W7164144082","https://openalex.org/W4297841344","https://openalex.org/W2782868226","https://openalex.org/W4312857924"],"abstract_inverted_index":{"Streaming":[0],"multilingual":[1],"speech":[2],"recognition":[3],"benefits":[4],"from":[5],"unified":[6,137,220],"systems":[7,26,118,227],"that":[8,35,71,208,218,234],"produce":[9],"numbers":[10],"in":[11,32,83,128,238,242,257],"their":[12,18],"written":[13],"form":[14,20,93,104],"'34'":[15],"rather":[16],"than":[17],"spoken":[19],"'thirty-four'.By":[21],"generating":[22],"digits":[23],"directly,":[24],"these":[25],"eliminate":[27],"the":[28,50,56,75,79,133,190,219,235,250],"post-processing":[29,157],"latency":[30],"inherent":[31],"cascaded":[33,153,226],"architectures":[34],"require":[36],"a":[37,45,91,96,102,107,136,151,156,162,171],"separate":[38],"inverse":[39],"text":[40],"normalization":[41],"(ITN)":[42],"step.Arabic":[43],"presents":[44],"formidable":[46],"challenge":[47],"for":[48,65,197,203],"ITN;":[49],"system":[51,143,191],"must":[52,89],"not":[53,212],"only":[54],"determine":[55],"correct":[57],"numerical":[58],"value":[59],"but":[60],"also":[61],"navigate":[62],"complex":[63],"rules":[64],"gender,":[66],"number,":[67],"and":[68,101,122,170,180,200,217,246],"case":[69,121],"marking":[70],"are":[72,240],"determined":[73],"by":[74,119],"counted":[76],"noun.For":[77],"instance,":[78],"digit":[80],"'7'":[81],"(as":[82],"'47')":[84],"exhibits":[85],"gender":[86,123,244],"polarity:":[87],"it":[88,149],"take":[90],"masculine":[92,108],"if":[94,105],"modifying":[95,106],"feminine":[97,103],"noun":[98,109],"(e.g.,":[99,110],"Halala)":[100],"Riyal).While":[111],"Arabic":[112,173,229],"dialects":[113],"typically":[114],"exhibit":[115],"simplified":[116],"numeral":[117],"omitting":[120],"markers,":[124],"they":[125],"vary":[126],"significantly":[127],"verbalization":[129],"patterns.This":[130],"study":[131],"explores":[132],"efficacy":[134],"of":[135,252],"streaming":[138,165],"Automatic":[139],"Speech":[140],"Recognition":[141],"(ASR)":[142],"with":[144,225],"integrated":[145],"ITN":[146,159,204,210,239],"features,":[147],"comparing":[148],"against":[150],"traditional":[152],"approach":[154],"utilizing":[155],"rule-based":[158],"module.We":[160],"utilize":[161],"FastConformer":[163],"cache-aware":[164],"model":[166,221],"trained":[167],"on":[168],"English":[169],"diverse":[172],"corpus":[174],"spanning":[175],"Modern":[176],"Standard":[177],"(MSA),":[178],"dialectal,":[179],"Classical":[181],"Arabic,":[182],"while":[183],"maintaining":[184],"diacritics":[185],"where":[186],"contextually":[187],"appropriate.We":[188],"evaluate":[189],"using":[192],"Word":[193],"Error":[194],"Rate":[195],"(WER)":[196],"ASR":[198,215],"accuracy":[199,223],"exact":[201],"match":[202],"capability.Our":[205],"results":[206],"demonstrate":[207],"integrating":[209],"does":[211],"degrade":[213],"core":[214],"performance":[216],"achieves":[222],"competitive":[224],"across":[228],"variants.However,":[230],"error":[231],"analysis":[232],"reveals":[233],"primary":[236],"failures":[237],"rooted":[241],"diacritization,":[243],"polarity,":[245],"orthographic":[247],"variation,":[248],"highlighting":[249],"challenges":[251],"Arabic's":[253],"unique":[254],"linguistic":[255],"features":[256],"end-to-end":[258],"modeling.":[259]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-06-30T00:00:00"}