{"id":"https://openalex.org/W4386566596","doi":"https://doi.org/10.18653/v1/2023.fieldmatters-1.8","title":"AraDiaWER: An Explainable Metric For Dialectical Arabic ASR","display_name":"AraDiaWER: An Explainable Metric For Dialectical Arabic ASR","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386566596","doi":"https://doi.org/10.18653/v1/2023.fieldmatters-1.8"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.fieldmatters-1.8","doi":"https://doi.org/10.18653/v1/2023.fieldmatters-1.8","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.fieldmatters-1.8","pdf_url":"https://aclanthology.org/2023.fieldmatters-1.8.pdf","source":{"id":"https://openalex.org/S7407119875","display_name":"Workshop on NLP Applications to Field Linguistics (Field Matters)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"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 Second Workshop on NLP Applications to Field Linguistics","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.fieldmatters-1.8.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065376162","display_name":"Abdulwahab Sahyoun","orcid":"https://orcid.org/0000-0002-8873-4388","observed_orcids":["https://orcid.org/0000-0002-8873-4388"]},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]},{"id":"https://openalex.org/I91044093","display_name":"Zayed University","ror":"https://ror.org/03snqfa66","country_code":"AE","type":"education","lineage":["https://openalex.org/I91044093"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Abdulwahab Sahyoun","raw_affiliation_strings":["Zayed University of Artificial Intelligence Abu Dhabi , United Arab Emirates","Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi, United Arab Emirates"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zayed University of Artificial Intelligence Abu Dhabi , United Arab Emirates","institution_ids":["https://openalex.org/I4210113480","https://openalex.org/I91044093"]},{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075022926","display_name":"Shady Shehata","orcid":"https://orcid.org/0000-0002-3258-6734","observed_orcids":["https://orcid.org/0000-0002-3258-6734"]},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]},{"id":"https://openalex.org/I91044093","display_name":"Zayed University","ror":"https://ror.org/03snqfa66","country_code":"AE","type":"education","lineage":["https://openalex.org/I91044093"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Shady Shehata","raw_affiliation_strings":["Zayed University of Artificial Intelligence Abu Dhabi , United Arab Emirates","Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi, United Arab Emirates"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zayed University of Artificial Intelligence Abu Dhabi , United Arab Emirates","institution_ids":["https://openalex.org/I4210113480","https://openalex.org/I91044093"]},{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3544,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53927711,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"64","last_page":"73"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.0003000000142492354,"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":9.999999747378752e-05,"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/word-error-rate","display_name":"word error rate","score":0.7289999723434448},{"id":"https://openalex.org/keywords/egyptian-arabic","display_name":"Egyptian Arabic","score":0.7179999947547913},{"id":"https://openalex.org/keywords/language-model-embeddings","display_name":"language model embeddings","score":0.8289999961853027},{"id":"https://openalex.org/keywords/minilm","display_name":"MiniLM","score":0.6629999876022339},{"id":"https://openalex.org/keywords/approximate-string-matching","display_name":"approximate string matching","score":0.6660000085830688},{"id":"https://openalex.org/keywords/low-resource-dialects","display_name":"low-resource dialects","score":0.843999981880188},{"id":"https://openalex.org/keywords/linguistic-variability","display_name":"linguistic variability","score":0.6000000238418579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8391236066818237},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7181394100189209},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6367154121398926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6126498579978943},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5441123843193054},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.493328720331192},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.43488526344299316},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41495048999786377},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40593230724334717},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24357253313064575},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.fieldmatters-1.8","doi":"https://doi.org/10.18653/v1/2023.fieldmatters-1.8","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.fieldmatters-1.8","pdf_url":"https://aclanthology.org/2023.fieldmatters-1.8.pdf","source":{"id":"https://openalex.org/S7407119875","display_name":"Workshop on NLP Applications to Field Linguistics (Field Matters)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"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 Second Workshop on NLP Applications to Field Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.fieldmatters-1.8","doi":"https://doi.org/10.18653/v1/2023.fieldmatters-1.8","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.fieldmatters-1.8","pdf_url":"https://aclanthology.org/2023.fieldmatters-1.8.pdf","source":{"id":"https://openalex.org/S7407119875","display_name":"Workshop on NLP Applications to Field Linguistics (Field Matters)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"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 Second Workshop on NLP Applications to Field Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386566596.pdf","grobid_xml":"https://content.openalex.org/works/W4386566596.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1630657132","https://openalex.org/W1990501283","https://openalex.org/W2756127416","https://openalex.org/W2785413227","https://openalex.org/W2786234940","https://openalex.org/W2787420813","https://openalex.org/W2798685342","https://openalex.org/W2900737918","https://openalex.org/W2963555443","https://openalex.org/W2972401849","https://openalex.org/W3008374555","https://openalex.org/W3036601975","https://openalex.org/W3047724560","https://openalex.org/W3134155512","https://openalex.org/W3147792899","https://openalex.org/W3169320628","https://openalex.org/W3205231356","https://openalex.org/W4300963525","https://openalex.org/W4311000453"],"related_works":["https://openalex.org/W7214764980","https://openalex.org/W2759178327","https://openalex.org/W1630657132","https://openalex.org/W2806225106","https://openalex.org/W7162195273","https://openalex.org/W7166571686","https://openalex.org/W7140135169","https://openalex.org/W4417169576","https://openalex.org/W3092459676","https://openalex.org/W4415402133"],"abstract_inverted_index":{"Linguistic":[0],"variability":[1],"poses":[2],"a":[3,111,132,148],"challenge":[4],"to":[5,44,83,115,138,151,166],"many":[6],"modern":[7],"ASR":[8,14,50,55,81,141,171],"systems,":[9,64],"particularly":[10],"Dialectical":[11,59],"Arabic":[12,60],"(DA)":[13,61],"systems":[15],"dealing":[16],"with":[17],"lowresource":[18],"dialects":[19],"and":[20,23,28,77,102,107,155],"resulting":[21],"morphological":[22,106],"orthographic":[24],"variations":[25],"in":[26,173],"text":[27],"speech.Traditional":[29],"evaluation":[30,56,176],"metrics":[31],"such":[32],"as":[33,147],"the":[34,67,75,94,117,122,144,168,174],"word":[35],"error":[36],"rate":[37],"(WER)":[38],"inadequately":[39],"capture":[40],"these":[41],"complexities,":[42],"leading":[43],"an":[45,54],"incomplete":[46],"assessment":[47],"of":[48,80,124,170],"DA":[49,140],"performance.We":[51],"propose":[52],"AraDiaWER,":[53],"metric":[57,146],"for":[58,74],"speech":[62],"recognition":[63],"focused":[65],"on":[66],"Egyptian":[68],"dialect.AraDi-aWER":[69],"uses":[70],"language":[71,127],"model":[72,128],"embeddings":[73,172],"syntactic":[76,118,154],"semantic":[78,95,156],"aspects":[79],"errors":[82],"identify":[84],"their":[85],"root":[86],"cause,":[87],"not":[88,158],"captured":[89],"by":[90,160],"traditional":[91],"WER.MiniLM":[92],"generates":[93],"score,":[96],"capturing":[97,153],"contextual":[98],"differences":[99],"between":[100],"reference":[101],"predicted":[103],"transcripts.CAMeLBERT-Mix":[104],"assigns":[105],"lexical":[108],"tags":[109],"using":[110],"fuzzy":[112],"matching":[113],"algorithm":[114],"calculate":[116],"score.Our":[119],"experiments":[120],"validate":[121],"effectiveness":[123],"Ara-DiaWER.By":[125],"incorporating":[126],"embeddings,":[129],"AraDiaWER":[130],"enables":[131],"more":[133],"interpretable":[134],"evaluation,":[135],"allowing":[136],"us":[137],"improve":[139],"systems.We":[142],"position":[143],"proposed":[145,175],"complementary":[149],"tool":[150],"WER,":[152],"features":[157],"represented":[159],"WER.Additionally,":[161],"we":[162],"use":[163],"UMAP":[164],"analysis":[165],"observe":[167],"quality":[169],"framework.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2023-09-10T00:00:00"}