{"id":"https://openalex.org/W7131669067","doi":"https://doi.org/10.1007/s11042-026-21395-3","title":"Transformer encoder and data augmentation for real-time speech emotion recognition","display_name":"Transformer encoder and data augmentation for real-time speech emotion recognition","publication_year":2026,"publication_date":"2026-02-26","ids":{"openalex":"https://openalex.org/W7131669067","doi":"https://doi.org/10.1007/s11042-026-21395-3"},"language":"en","primary_location":{"id":"doi:10.1007/s11042-026-21395-3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11042-026-21395-3","pdf_url":null,"source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-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/A5015721059","display_name":"Chawki Barhoumi","orcid":"https://orcid.org/0000-0003-4741-8036"},"institutions":[{"id":"https://openalex.org/I142899784","display_name":"University of Sfax","ror":"https://ror.org/04d4sd432","country_code":"TN","type":"education","lineage":["https://openalex.org/I142899784"]},{"id":"https://openalex.org/I4210131288","display_name":"National Engineering School of Tunis","ror":"https://ror.org/03b1zjt31","country_code":"TN","type":"education","lineage":["https://openalex.org/I4210131288","https://openalex.org/I63596082"]}],"countries":["TN"],"is_corresponding":true,"raw_author_name":"Chawki Barhoumi","raw_affiliation_strings":["Multimedia, Information systems and Advanced Computing Laboratory, Sfax, 3021, Tunisia","National School of Electronics and Telecommunications, Sfax, 3027, Tunisia"],"affiliations":[{"raw_affiliation_string":"Multimedia, Information systems and Advanced Computing Laboratory, Sfax, 3021, Tunisia","institution_ids":["https://openalex.org/I142899784"]},{"raw_affiliation_string":"National School of Electronics and Telecommunications, Sfax, 3027, Tunisia","institution_ids":["https://openalex.org/I142899784","https://openalex.org/I4210131288"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005772397","display_name":"Yassine BenAyed","orcid":null},"institutions":[{"id":"https://openalex.org/I142899784","display_name":"University of Sfax","ror":"https://ror.org/04d4sd432","country_code":"TN","type":"education","lineage":["https://openalex.org/I142899784"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Yassine BenAyed","raw_affiliation_strings":["Multimedia, Information systems and Advanced Computing Laboratory, Sfax, 3021, Tunisia"],"affiliations":[{"raw_affiliation_string":"Multimedia, Information systems and Advanced Computing Laboratory, Sfax, 3021, Tunisia","institution_ids":["https://openalex.org/I142899784"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5015721059"],"corresponding_institution_ids":["https://openalex.org/I142899784","https://openalex.org/I4210131288"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74374147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"85","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.0020000000949949026,"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/T10863","display_name":"Voice and Speech Disorders","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7343999743461609},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6852999925613403},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5321000218391418},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5041000247001648},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.49079999327659607},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4675999879837036},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46309998631477356},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.4404999911785126},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4359000027179718},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41690000891685486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8824999928474426},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7343999743461609},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6948999762535095},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6852999925613403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5464000105857849},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5321000218391418},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5041000247001648},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49079999327659607},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4675999879837036},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46309998631477356},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.4404999911785126},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4359000027179718},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3849000036716461},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.36169999837875366},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3379000127315521},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.31380000710487366},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3052000105381012},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29989999532699585},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.29899999499320984},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2944999933242798},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.289900004863739},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11042-026-21395-3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11042-026-21395-3","pdf_url":null,"source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W2191779130","https://openalex.org/W2407080277","https://openalex.org/W2724317853","https://openalex.org/W2803193013","https://openalex.org/W2969889150","https://openalex.org/W2974062151","https://openalex.org/W3015240477","https://openalex.org/W3109943296","https://openalex.org/W3126625480","https://openalex.org/W3204215166","https://openalex.org/W3207346153","https://openalex.org/W4226153164","https://openalex.org/W4285144065","https://openalex.org/W4293778726","https://openalex.org/W4313549077","https://openalex.org/W4319596491","https://openalex.org/W4323569712","https://openalex.org/W4364378283","https://openalex.org/W4372348599","https://openalex.org/W4383219119","https://openalex.org/W4383551941","https://openalex.org/W4385128072","https://openalex.org/W4385258623","https://openalex.org/W4385382111","https://openalex.org/W4386041382","https://openalex.org/W4386068662","https://openalex.org/W4386524296","https://openalex.org/W4387261468","https://openalex.org/W4387398498","https://openalex.org/W4387846988","https://openalex.org/W4388705468","https://openalex.org/W4389400979","https://openalex.org/W4393861110","https://openalex.org/W4393977829","https://openalex.org/W4394063698","https://openalex.org/W4399134373","https://openalex.org/W4399434529","https://openalex.org/W4400041227","https://openalex.org/W4401808502","https://openalex.org/W4402095521","https://openalex.org/W4403869449","https://openalex.org/W4405654358","https://openalex.org/W4408358330","https://openalex.org/W4410539370","https://openalex.org/W4411565457"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-02-27T06:22:10.598206","created_date":"2026-02-27T00:00:00"}
