{"id":"https://openalex.org/W4408354688","doi":"https://doi.org/10.1109/icassp49660.2025.10889643","title":"Open Automatic Speech Recognition Models for Classical and Modern Standard Arabic","display_name":"Open Automatic Speech Recognition Models for Classical and Modern Standard Arabic","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354688","doi":"https://doi.org/10.1109/icassp49660.2025.10889643"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889643","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889643","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5102911821","display_name":"L. A. Grigoryan","orcid":"https://orcid.org/0000-0002-6535-6185"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lilit Grigoryan","raw_affiliation_strings":["NVIDIA,Yerevan,Armenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,Yerevan,Armenia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066709803","display_name":"Nikolay Karpov","orcid":"https://orcid.org/0000-0003-1053-5239"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikolay Karpov","raw_affiliation_strings":["NVIDIA,Yerevan,Armenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,Yerevan,Armenia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116594514","display_name":"Enas Albasiri","orcid":null},"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,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026088310","display_name":"Vitaly Lavrukhin","orcid":"https://orcid.org/0009-0006-7866-8301"},"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":"Vitaly Lavrukhin","raw_affiliation_strings":["NVIDIA,Santa Clara,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032957280","display_name":"Boris Ginsburg","orcid":null},"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":"Boris Ginsburg","raw_affiliation_strings":["NVIDIA,Santa Clara,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,Santa Clara,USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85591274,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9829999804496765,"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":0.9829999804496765,"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/computer-science","display_name":"Computer science","score":0.7361268997192383},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6763811111450195},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.6223398447036743},{"id":"https://openalex.org/keywords/modern-standard-arabic","display_name":"Modern Standard Arabic","score":0.6000242829322815},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5128229260444641},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4579869508743286},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18674233555793762}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7361268997192383},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6763811111450195},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6223398447036743},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.6000242829322815},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5128229260444641},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4579869508743286},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18674233555793762},{"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/icassp49660.2025.10889643","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889643","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1529112607","https://openalex.org/W1990501283","https://openalex.org/W2127141656","https://openalex.org/W2144189802","https://openalex.org/W2144499799","https://openalex.org/W2189369791","https://openalex.org/W2293634267","https://openalex.org/W2402146185","https://openalex.org/W2538777612","https://openalex.org/W2586619907","https://openalex.org/W2760231680","https://openalex.org/W2891290234","https://openalex.org/W2936774411","https://openalex.org/W2940606701","https://openalex.org/W2962780374","https://openalex.org/W2963077089","https://openalex.org/W2972808286","https://openalex.org/W2996456791","https://openalex.org/W3015537910","https://openalex.org/W3097777922","https://openalex.org/W3159891521","https://openalex.org/W3167101391","https://openalex.org/W3194921972","https://openalex.org/W3197295304","https://openalex.org/W3198739096","https://openalex.org/W4319862635","https://openalex.org/W4319862671","https://openalex.org/W4385245566","https://openalex.org/W4385822324","https://openalex.org/W4389518360","https://openalex.org/W4389518430","https://openalex.org/W4391021542","https://openalex.org/W6631362777","https://openalex.org/W6640090968","https://openalex.org/W6691373038","https://openalex.org/W6771467084","https://openalex.org/W6793199777","https://openalex.org/W6810007534","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2620283452","https://openalex.org/W3204019825","https://openalex.org/W4322750817","https://openalex.org/W4400896925","https://openalex.org/W4396221470","https://openalex.org/W587642979","https://openalex.org/W2489270562","https://openalex.org/W2894059694","https://openalex.org/W4403231732","https://openalex.org/W4299493485"],"abstract_inverted_index":{"Despite":[0],"Arabic":[1,13,34,48,69,113],"being":[2],"one":[3,95],"of":[4,12,32,40,79],"the":[5,10,24,41,57,60,80,92,101,103,130,151],"most":[6],"widely":[7],"spoken":[8],"languages,":[9],"development":[11],"Automatic":[14],"Speech":[15],"Recognition":[16],"(ASR)":[17],"systems":[18],"faces":[19],"significant":[20],"challenges":[21,78],"due":[22],"to":[23,56,75],"language\u2019s":[25],"complexity,":[26],"and":[27,71,100,111,153],"only":[28],"a":[29,65,119],"limited":[30],"number":[31],"public":[33,106],"ASR":[35],"models":[36,89,152],"exist.":[37],"While":[38],"much":[39],"focus":[42],"has":[43],"been":[44],"on":[45,91,126],"Modern":[46],"Standard":[47],"(MSA),":[49],"there":[50],"is":[51],"considerably":[52],"less":[53],"attention":[54],"given":[55],"variations":[58],"within":[59],"language.":[61,81],"This":[62],"paper":[63],"introduces":[64],"universal":[66],"methodology":[67],"for":[68,98,108,138,144],"speech":[70],"text":[72],"processing":[73],"designed":[74,96],"address":[76],"unique":[77],"Using":[82],"this":[83],"methodology,":[84],"we":[85,149],"train":[86],"two":[87],"novel":[88],"based":[90],"FastConformer":[93],"architecture:":[94],"specifically":[97],"MSA":[99,110,116],"other,":[102],"first":[104],"unified":[105,131],"model":[107,117,132],"both":[109],"Classical":[112],"(CA).":[114],"The":[115],"sets":[118],"new":[120],"benchmark":[121],"with":[122,136],"state-of-the-art":[123],"(SOTA)":[124],"performance":[125,143],"related":[127],"datasets,":[128],"while":[129,140],"achieves":[133],"SOTA":[134],"accuracy":[135],"diacritics":[137],"CA":[139],"maintaining":[141],"strong":[142],"MSA.":[145],"To":[146],"promote":[147],"reproducibility,":[148],"open-source":[150],"their":[154],"training":[155],"recipes.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}