{"id":"https://openalex.org/W3091088345","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206658","title":"Multi-Dialect Arabic Speech Recognition","display_name":"Multi-Dialect Arabic Speech Recognition","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3091088345","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206658","mag":"3091088345"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9206658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2112.14678","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065688744","display_name":"Abbas Raza Ali","orcid":"https://orcid.org/0000-0003-0505-2638"},"institutions":[{"id":"https://openalex.org/I9300472","display_name":"Bournemouth University","ror":"https://ror.org/05wwcw481","country_code":"GB","type":"education","lineage":["https://openalex.org/I9300472"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Abbas Raza Ali","raw_affiliation_strings":["Faculty of Science and Technology, Bournemouth University, Poole, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Science and Technology, Bournemouth University, Poole, United Kingdom","institution_ids":["https://openalex.org/I9300472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5065688744"],"corresponding_institution_ids":["https://openalex.org/I9300472"],"apc_list":null,"apc_paid":null,"fwci":1.0408,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.82372483,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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/T10860","display_name":"Speech and Audio Processing","score":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.8299514651298523},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8138316869735718},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7257266640663147},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6819777488708496},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6171582341194153},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5629181265830994},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic","score":0.5162953734397888},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5157814025878906},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.49831128120422363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4866819977760315},{"id":"https://openalex.org/keywords/beam-search","display_name":"Beam search","score":0.4687654674053192},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44515782594680786},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.420604944229126},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3351965546607971},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3138474225997925},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.17413675785064697},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07758593559265137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8299514651298523},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8138316869735718},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7257266640663147},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6819777488708496},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6171582341194153},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5629181265830994},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.5162953734397888},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5157814025878906},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.49831128120422363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4866819977760315},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.4687654674053192},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44515782594680786},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.420604944229126},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3351965546607971},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3138474225997925},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.17413675785064697},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07758593559265137},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9206658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2112.14678","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.14678","pdf_url":"https://arxiv.org/pdf/2112.14678","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2112.14678","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2112.14678","pdf_url":"https://arxiv.org/pdf/2112.14678","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1515135274","https://openalex.org/W1533861849","https://openalex.org/W1922655562","https://openalex.org/W2024742853","https://openalex.org/W2091562353","https://openalex.org/W2102113734","https://openalex.org/W2141440284","https://openalex.org/W2143612262","https://openalex.org/W2153364078","https://openalex.org/W2193413348","https://openalex.org/W2293183352","https://openalex.org/W2340701013","https://openalex.org/W2399262366","https://openalex.org/W2402146185","https://openalex.org/W2557702360","https://openalex.org/W2585345551","https://openalex.org/W2586568968","https://openalex.org/W2586619907","https://openalex.org/W2620586161","https://openalex.org/W2787420813","https://openalex.org/W2895892321","https://openalex.org/W2963077089","https://openalex.org/W2964121744","https://openalex.org/W6631943919","https://openalex.org/W6640090968","https://openalex.org/W6675365184","https://openalex.org/W6680768788","https://openalex.org/W6687566353","https://openalex.org/W6712656597","https://openalex.org/W6712930963","https://openalex.org/W6727048030","https://openalex.org/W6730585245"],"related_works":["https://openalex.org/W1840351222","https://openalex.org/W71447404","https://openalex.org/W151018310","https://openalex.org/W3081187864","https://openalex.org/W4380605396","https://openalex.org/W2803306015","https://openalex.org/W3133352777","https://openalex.org/W2008737763","https://openalex.org/W2784059283","https://openalex.org/W4319779560"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,33,44,57,64,81,109,138,144,152,159,167],"design":[4],"and":[5,53,131,149],"development":[6,65,110],"of":[7,32,43,46,50,60,66,111,126,129,137],"multi-dialect":[8],"automatic":[9],"speech":[10,36],"recognition":[11,37],"for":[12],"Arabic.":[13],"Deep":[14],"neural":[15],"networks":[16],"are":[17,98,141,162],"becoming":[18],"an":[19,29,116],"effective":[20],"tool":[21],"to":[22,114,165],"solve":[23],"sequential":[24],"data":[25,140],"problems,":[26],"particularly,":[27],"adopting":[28],"end-to-end":[30],"training":[31],"system.":[34],"Arabic":[35,93],"is":[38,63,108,178],"a":[39,67,102,112,127,181,186,194],"complex":[40],"task":[41],"because":[42],"existence":[45],"multiple":[47,88],"dialects,":[48],"non-availability":[49],"large":[51,68],"corpora,":[52],"missing":[54],"vocalization.":[55],"Thus,":[56],"first":[58],"contribution":[59,107],"this":[61],"work":[62],"multi-dialectal":[69],"corpus":[70,83],"with":[71,170,185],"either":[72],"full":[73],"or":[74],"at":[75],"least":[76],"partially":[77],"vocalized":[78],"transcription.":[79],"Additionally,":[80],"open-source":[82],"has":[84],"been":[85],"gathered":[86],"from":[87],"sources":[89],"that":[90],"bring":[91],"non-standard":[92],"alphabets":[94],"in":[95,143,151],"transcription":[96,173],"which":[97,198],"normalized":[99],"by":[100,158],"defining":[101],"common":[103],"character-set.":[104],"The":[105,122,134,154,175,190],"second":[106],"framework":[113],"train":[115],"acoustic":[117],"model":[118],"achieving":[119],"state-of-the-art":[120],"performance.":[121],"network":[123],"architecture":[124],"comprises":[125],"combination":[128],"convolutional":[130],"recurrent":[132,160],"layers.":[133],"spectrogram":[135],"features":[136,169],"audio":[139,168],"extracted":[142],"frequency":[145],"vs":[146],"time":[147],"domain":[148],"fed":[150],"network.":[153],"output":[155],"frames,":[156],"produced":[157],"model,":[161],"further":[163],"trained":[164],"align":[166],"its":[171],"corresponding":[172],"sequences.":[174],"sequence":[176],"alignment":[177],"performed":[179],"using":[180],"beam":[182],"search":[183],"decoder":[184],"tetra-gram":[187],"language":[188],"model.":[189],"proposed":[191],"system":[192],"achieved":[193],"14%":[195],"error":[196],"rate":[197],"outperforms":[199],"previous":[200],"systems.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}