{"id":"https://openalex.org/W4405654358","doi":"https://doi.org/10.1007/s10462-024-11065-x","title":"Real-time speech emotion recognition using deep learning and data augmentation","display_name":"Real-time speech emotion recognition using deep learning and data augmentation","publication_year":2024,"publication_date":"2024-12-19","ids":{"openalex":"https://openalex.org/W4405654358","doi":"https://doi.org/10.1007/s10462-024-11065-x"},"language":"en","primary_location":{"id":"doi:10.1007/s10462-024-11065-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-024-11065-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-024-11065-x.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10462-024-11065-x.pdf","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"]}],"countries":["TN"],"is_corresponding":true,"raw_author_name":"Chawki Barhoumi","raw_affiliation_strings":["Multimedia, InfoRmation systems and Advanced Computing Laboratory, 3027, Sfax, Tunisia","National School of Electronics and Telecommunications of Sfax, 3027, Sfax, Tunisia"],"affiliations":[{"raw_affiliation_string":"Multimedia, InfoRmation systems and Advanced Computing Laboratory, 3027, Sfax, Tunisia","institution_ids":["https://openalex.org/I142899784"]},{"raw_affiliation_string":"National School of Electronics and Telecommunications of Sfax, 3027, Sfax, Tunisia","institution_ids":["https://openalex.org/I142899784"]}]},{"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, 3027, Sfax, Tunisia"],"affiliations":[{"raw_affiliation_string":"Multimedia, InfoRmation systems and Advanced Computing Laboratory, 3027, Sfax, 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"],"apc_list":{"value":2490,"currency":"EUR","value_usd":3090},"apc_paid":{"value":2490,"currency":"EUR","value_usd":3090},"fwci":14.1978,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.99249454,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"58","issue":"2","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":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"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/T11448","display_name":"Face recognition and analysis","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7802076935768127},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6597713232040405},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6541520357131958},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5341203808784485},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.447252094745636}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7802076935768127},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6597713232040405},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6541520357131958},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5341203808784485},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.447252094745636}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10462-024-11065-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-024-11065-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-024-11065-x.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10462-024-11065-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-024-11065-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-024-11065-x.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405654358.pdf","grobid_xml":"https://content.openalex.org/works/W4405654358.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W175750906","https://openalex.org/W786031425","https://openalex.org/W1536822605","https://openalex.org/W1538482441","https://openalex.org/W2003837801","https://openalex.org/W2009059481","https://openalex.org/W2032254851","https://openalex.org/W2061068689","https://openalex.org/W2074788634","https://openalex.org/W2102267302","https://openalex.org/W2156503193","https://openalex.org/W2158061940","https://openalex.org/W2162772395","https://openalex.org/W2181741066","https://openalex.org/W2436394355","https://openalex.org/W2724317853","https://openalex.org/W2768978460","https://openalex.org/W2773080983","https://openalex.org/W2782874754","https://openalex.org/W2792191740","https://openalex.org/W2795882013","https://openalex.org/W2803193013","https://openalex.org/W2955120364","https://openalex.org/W2959133507","https://openalex.org/W2969889150","https://openalex.org/W2970737019","https://openalex.org/W2997399314","https://openalex.org/W3000139089","https://openalex.org/W3007944646","https://openalex.org/W3089365109","https://openalex.org/W3095435288","https://openalex.org/W3096262466","https://openalex.org/W3109943296","https://openalex.org/W3109961563","https://openalex.org/W3126625480","https://openalex.org/W3136524425","https://openalex.org/W3169393150","https://openalex.org/W3174901184","https://openalex.org/W3198724388","https://openalex.org/W3208745384","https://openalex.org/W4220894258","https://openalex.org/W4221046698","https://openalex.org/W4224001749","https://openalex.org/W4225854086","https://openalex.org/W4226207398","https://openalex.org/W4246648570","https://openalex.org/W4285144065","https://openalex.org/W4309965782","https://openalex.org/W4316661260","https://openalex.org/W4319596491","https://openalex.org/W4364378283","https://openalex.org/W4385382111"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W3009238340","https://openalex.org/W4360585206","https://openalex.org/W4321369474","https://openalex.org/W4285208911","https://openalex.org/W3082895349","https://openalex.org/W4213079790","https://openalex.org/W2248239756","https://openalex.org/W3086377361"],"abstract_inverted_index":{"In":[0,51],"human\u2013human":[1],"interactions,":[2,23],"detecting":[3,24],"emotions":[4,46],"is":[5],"often":[6],"easy":[7],"as":[8,71,96],"it":[9],"can":[10,27],"be":[11,28],"perceived":[12],"through":[13,48],"facial":[14],"expressions,":[15],"body":[16],"gestures,":[17],"or":[18],"speech.":[19],"However,":[20],"in":[21,176],"human\u2013machine":[22],"human":[25],"emotion":[26,204],"a":[29,56,142],"challenge.":[30],"To":[31,77],"improve":[32],"this":[33,52],"interaction,":[34],"Speech":[35],"Emotion":[36],"Recognition":[37],"(SER)":[38],"has":[39],"emerged,":[40],"with":[41,148,196],"the":[42,79,117,164,183,186,200],"goal":[43],"of":[44,185],"recognizing":[45],"solely":[47],"vocal":[49,120],"intonation.":[50],"work,":[53],"we":[54,82,159],"propose":[55],"SER":[57],"system":[58],"based":[59,192],"on":[60,193],"deep":[61,128,188],"learning":[62,129,189],"approaches":[63],"and":[64,74,89,113,141],"two":[65],"efficient":[66],"data":[67,197],"augmentation":[68,198],"techniques":[69],"such":[70,95],"noise":[72],"addition":[73],"spectrogram":[75],"shifting.":[76],"evaluate":[78],"proposed":[80,187,201],"system,":[81],"used":[83],"three":[84],"different":[85,127,157],"datasets:":[86],"TESS,":[87],"EmoDB,":[88],"RAVDESS.":[90],"We":[91],"employe":[92],"several":[93],"algorithms":[94],"Mel":[97,106],"Frequency":[98],"Cepstral":[99],"Coefficients":[100],"(MFCC),":[101],"Zero":[102],"Crossing":[103],"Rate":[104],"(ZCR),":[105],"spectrograms,":[107],"Root":[108],"Mean":[109],"Square":[110],"Value":[111],"(RMS),":[112],"chroma":[114],"to":[115,162],"select":[116],"most":[118,165],"appropriate":[119],"features":[121],"that":[122,145],"represent":[123],"speech":[124,174,203],"emotions.":[125],"Three":[126],"models":[130],"were":[131,160],"imployed,":[132],"including":[133],"MultiLayer":[134],"Perceptron":[135],"(MLP),":[136],"Convolutional":[137],"Neural":[138],"Network":[139],"(CNN),":[140],"hybrid":[143],"model":[144,167],"combines":[146],"CNN":[147],"Bidirectional":[149],"Long-Short":[150],"Term":[151],"Memory":[152],"(Bi-LSTM).":[153],"By":[154],"exploring":[155],"these":[156],"approaches,":[158],"able":[161],"identify":[163],"effective":[166],"for":[168,199],"accurately":[169],"identifying":[170],"emotional":[171],"states":[172],"from":[173],"signals":[175],"real-time":[177,202],"situation.":[178],"Overall,":[179],"our":[180],"work":[181],"demonstrates":[182],"effectiveness":[184],"model,":[190],"specifically":[191],"CNN+BiLSTM":[194],"enhanced":[195],"recognition.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":23}],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2025-10-10T00:00:00"}