{"id":"https://openalex.org/W4399343167","doi":"https://doi.org/10.11591/ijeecs.v35.i2.pp1013-1021","title":"AMSVT: audio Mel-spectrogram vision transformer for spoken Arabic digit recognition","display_name":"AMSVT: audio Mel-spectrogram vision transformer for spoken Arabic digit recognition","publication_year":2024,"publication_date":"2024-06-04","ids":{"openalex":"https://openalex.org/W4399343167","doi":"https://doi.org/10.11591/ijeecs.v35.i2.pp1013-1021"},"language":"en","primary_location":{"id":"doi:10.11591/ijeecs.v35.i2.pp1013-1021","doi":"https://doi.org/10.11591/ijeecs.v35.i2.pp1013-1021","is_oa":true,"landing_page_url":"https://doi.org/10.11591/ijeecs.v35.i2.pp1013-1021","pdf_url":"https://ijeecs.iaescore.com/index.php/IJEECS/article/download/36762/18487","source":{"id":"https://openalex.org/S2764855249","display_name":"Indonesian Journal of Electrical Engineering and Computer Science","issn_l":"2502-4752","issn":["2502-4752","2502-4760"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1","poland-20","russia-white-list-2"],"host_organization":"https://openalex.org/P4310315009","host_organization_name":"Institute of Advanced Engineering and Science (IAES)","host_organization_lineage":["https://openalex.org/P4310315009"],"host_organization_lineage_names":["Institute of Advanced Engineering and Science (IAES)"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Indonesian Journal of Electrical Engineering and Computer Science","raw_type":"journal-article"},"parent_works":[],"lineage":["https://openalex.org/W4399343167"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ijeecs.iaescore.com/index.php/IJEECS/article/download/36762/18487","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005732856","display_name":"Omayma Mahmoudi","orcid":"https://orcid.org/0000-0003-3211-6633","observed_orcids":["https://orcid.org/0000-0003-3211-6633"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Omayma Mahmoudi","raw_affiliation_strings":["Mohammed Premier University"],"raw_orcid":"https://orcid.org/0000-0003-3211-6633","affiliations":[{"raw_affiliation_string":"Mohammed Premier University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003047793","display_name":"Naoufal El Allali","orcid":"https://orcid.org/0000-0002-6640-9672","observed_orcids":["https://orcid.org/0000-0002-6640-9672"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naoufal El Allali","raw_affiliation_strings":["Mohammed Premier University"],"raw_orcid":"https://orcid.org/0000-0002-6640-9672","affiliations":[{"raw_affiliation_string":"Mohammed Premier University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059333976","display_name":"Mouncef Filali Bouami","orcid":"https://orcid.org/0000-0001-5244-2589","observed_orcids":["https://orcid.org/0000-0001-5244-2589"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mouncef Filali Bouami","raw_affiliation_strings":["Mohammed Premier University"],"raw_orcid":"https://orcid.org/0000-0001-5244-2589","affiliations":[{"raw_affiliation_string":"Mohammed Premier University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4162,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.5755775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"35","issue":"2","first_page":"1013","last_page":"1013"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9477999806404114,"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":0.9477999806404114,"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":0.04100000113248825,"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":0.008299999870359898,"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/vision-transformer","display_name":"vision transformer","score":0.968999981880188},{"id":"https://openalex.org/keywords/spoken-digit-recognition","display_name":"spoken digit recognition","score":0.5659999847412109}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8358672857284546},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.6915939450263977},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6864376068115234},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6626337766647339},{"id":"https://openalex.org/C94957134","wikidata":"https://www.wikidata.org/wiki/Q82990","display_name":"Numerical digit","level":2,"score":0.6483476161956787},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6182833313941956},{"id":"https://openalex.org/C2984784707","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Digit recognition","level":3,"score":0.43213921785354614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33685174584388733},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17489486932754517},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17020449042320251},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.10549551248550415},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07805061340332031},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.05500921607017517},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.05039644241333008},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"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:10.11591/ijeecs.v35.i2.pp1013-1021","doi":"https://doi.org/10.11591/ijeecs.v35.i2.pp1013-1021","is_oa":true,"landing_page_url":"https://doi.org/10.11591/ijeecs.v35.i2.pp1013-1021","pdf_url":"https://ijeecs.iaescore.com/index.php/IJEECS/article/download/36762/18487","source":{"id":"https://openalex.org/S2764855249","display_name":"Indonesian Journal of Electrical Engineering and Computer Science","issn_l":"2502-4752","issn":["2502-4752","2502-4760"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1","poland-20","russia-white-list-2"],"host_organization":"https://openalex.org/P4310315009","host_organization_name":"Institute of Advanced Engineering and Science (IAES)","host_organization_lineage":["https://openalex.org/P4310315009"],"host_organization_lineage_names":["Institute of Advanced Engineering and Science (IAES)"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Indonesian Journal of Electrical Engineering and Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.11591/ijeecs.v35.i2.pp1013-1021","doi":"https://doi.org/10.11591/ijeecs.v35.i2.pp1013-1021","is_oa":true,"landing_page_url":"https://doi.org/10.11591/ijeecs.v35.i2.pp1013-1021","pdf_url":"https://ijeecs.iaescore.com/index.php/IJEECS/article/download/36762/18487","source":{"id":"https://openalex.org/S2764855249","display_name":"Indonesian Journal of Electrical Engineering and Computer Science","issn_l":"2502-4752","issn":["2502-4752","2502-4760"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1","poland-20","russia-white-list-2"],"host_organization":"https://openalex.org/P4310315009","host_organization_name":"Institute of Advanced Engineering and Science (IAES)","host_organization_lineage":["https://openalex.org/P4310315009"],"host_organization_lineage_names":["Institute of Advanced Engineering and Science (IAES)"],"type":"journal"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Indonesian Journal of Electrical Engineering and Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399343167.pdf","grobid_xml":"https://content.openalex.org/works/W4399343167.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2971695166","https://openalex.org/W3006477068","https://openalex.org/W3007075806","https://openalex.org/W3014416193","https://openalex.org/W3114896399","https://openalex.org/W3139049060","https://openalex.org/W3141838378","https://openalex.org/W3146639881","https://openalex.org/W3162424363","https://openalex.org/W3164024107","https://openalex.org/W3175181340","https://openalex.org/W3190378193","https://openalex.org/W3199527474","https://openalex.org/W3206996142","https://openalex.org/W3209201410","https://openalex.org/W4221161923","https://openalex.org/W4283726963","https://openalex.org/W4286517983","https://openalex.org/W4287181170","https://openalex.org/W4308882396","https://openalex.org/W4312446817","https://openalex.org/W4367354769","https://openalex.org/W4381744765","https://openalex.org/W4385391093","https://openalex.org/W4385480633","https://openalex.org/W4386735199","https://openalex.org/W4393565162","https://openalex.org/W4400679783","https://openalex.org/W4409150647"],"related_works":["https://openalex.org/W6888884687","https://openalex.org/W7166297745","https://openalex.org/W3197596377","https://openalex.org/W4221161923","https://openalex.org/W4405616028","https://openalex.org/W2912430121","https://openalex.org/W2971695166","https://openalex.org/W2805663803","https://openalex.org/W4404573485","https://openalex.org/W4360942793"],"abstract_inverted_index":{"This":[0,90],"work":[1],"presents":[2],"a":[3,117],"novel":[4],"model":[5,55,115],"to":[6,15,31,35,77,111],"recognize":[7],"spoken":[8],"digits":[9],"in":[10,21,73,85,121],"the":[11,16,57,78,100],"Arabic":[12],"language.":[13],"Due":[14],"transformer-based":[17,33],"models'":[18],"tremendous":[19],"success":[20],"natural":[22],"language":[23],"processing":[24,68],"(NLP),":[25],"several":[26,86],"attempts":[27],"have":[28],"been":[29,71],"made":[30],"extend":[32],"designs":[34],"other":[36],"domains,":[37],"such":[38,127],"as":[39,97,109,128],"vision":[40,61,82,88,112],"and":[41,49,125,133],"audio.":[42],"However,":[43],"our":[44,54],"approach":[45],"consists":[46],"of":[47,56,81,119,123],"extracting":[48],"inputting":[50],"Mel-spectrogram":[51,60],"features":[52],"into":[53],"proposed":[58],"audio":[59],"transformer":[62],"(AMSVT)":[63],"for":[64,102],"training.":[65],"The":[66],"signal":[67],"community":[69],"has":[70],"interested":[72],"these":[74],"models":[75,120],"due":[76],"successful":[79],"use":[80],"transformers":[83],"(ViT)":[84],"computer":[87],"applications.":[89],"is":[91],"because":[92],"signals":[93],"are":[94],"frequently":[95],"recorded":[96],"spectrograms":[98],"(using":[99],"Mel-spectrogram,":[101],"example),":[103],"which":[104],"may":[105],"be":[106],"given":[107],"directly":[108],"input":[110],"transformers.":[113],"Our":[114],"outperformed":[116],"group":[118],"terms":[122],"accuracy":[124],"time,":[126],"convolutional":[129],"neural":[130,135],"network":[131,136],"(CNN)-based":[132],"recurrent":[134],"(RNN)-based.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-06-05T00:00:00"}
