{"id":"https://openalex.org/W4404762293","doi":"https://doi.org/10.3390/computers13120315","title":"Benchmarking Pretrained Models for Speech Emotion Recognition: A Focus on Xception","display_name":"Benchmarking Pretrained Models for Speech Emotion Recognition: A Focus on Xception","publication_year":2024,"publication_date":"2024-11-27","ids":{"openalex":"https://openalex.org/W4404762293","doi":"https://doi.org/10.3390/computers13120315"},"language":"en","primary_location":{"id":"doi:10.3390/computers13120315","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers13120315","pdf_url":null,"source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/computers13120315","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ahmed Hassan","orcid":"https://orcid.org/0009-0009-0218-9015"},"institutions":[{"id":"https://openalex.org/I4210100043","display_name":"Superior University","ror":"https://ror.org/00yh88643","country_code":"PK","type":"education","lineage":["https://openalex.org/I4210100043"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Ahmed Hassan","raw_affiliation_strings":["Faculty of Computer Science and Information Technology, Superior University, Lahore 54000, Pakistan"],"raw_orcid":"https://orcid.org/0009-0009-0218-9015","affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Information Technology, Superior University, Lahore 54000, Pakistan","institution_ids":["https://openalex.org/I4210100043"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023426318","display_name":"Tehreem Masood","orcid":"https://orcid.org/0000-0002-0103-9746"},"institutions":[{"id":"https://openalex.org/I4210100043","display_name":"Superior University","ror":"https://ror.org/00yh88643","country_code":"PK","type":"education","lineage":["https://openalex.org/I4210100043"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Tehreem Masood","raw_affiliation_strings":["Department of Software Engineering, Superior University, Lahore 54000, Pakistan","Faculty of Computer Science and Information Technology, Superior University, Lahore 54000, Pakistan"],"raw_orcid":"https://orcid.org/0000-0002-0103-9746","affiliations":[{"raw_affiliation_string":"Department of Software Engineering, Superior University, Lahore 54000, Pakistan","institution_ids":["https://openalex.org/I4210100043"]},{"raw_affiliation_string":"Faculty of Computer Science and Information Technology, Superior University, Lahore 54000, Pakistan","institution_ids":["https://openalex.org/I4210100043"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067106342","display_name":"Hassan A. Ahmed","orcid":"https://orcid.org/0000-0002-0683-532X"},"institutions":[{"id":"https://openalex.org/I102607778","display_name":"Cleveland State University","ror":"https://ror.org/002tx1f22","country_code":"US","type":"education","lineage":["https://openalex.org/I102607778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hassan A. Ahmed","raw_affiliation_strings":["Department of Information Systems, Monte Ahuja College of Business, Cleveland State University, Cleveland, OH 44114, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, Monte Ahuja College of Business, Cleveland State University, Cleveland, OH 44114, USA","institution_ids":["https://openalex.org/I102607778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037103657","display_name":"H. M. Shahzad","orcid":"https://orcid.org/0000-0002-2452-6571"},"institutions":[{"id":"https://openalex.org/I4210100043","display_name":"Superior University","ror":"https://ror.org/00yh88643","country_code":"PK","type":"education","lineage":["https://openalex.org/I4210100043"]}],"countries":["PK"],"is_corresponding":true,"raw_author_name":"H. M. Shahzad","raw_affiliation_strings":["Faculty of Computer Science and Information Technology, Superior University, Lahore 54000, Pakistan"],"raw_orcid":"https://orcid.org/0000-0002-2452-6571","affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Information Technology, Superior University, Lahore 54000, Pakistan","institution_ids":["https://openalex.org/I4210100043"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089664976","display_name":"Hafiz Muhammad Tayyab Khushi","orcid":"https://orcid.org/0000-0002-4386-1527"},"institutions":[{"id":"https://openalex.org/I4210100043","display_name":"Superior University","ror":"https://ror.org/00yh88643","country_code":"PK","type":"education","lineage":["https://openalex.org/I4210100043"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Hafiz Muhammad Tayyab Khushi","raw_affiliation_strings":["Department of Software Engineering, Superior University, Lahore 54000, Pakistan","Faculty of Computer Science and Information Technology, Superior University, Lahore 54000, Pakistan"],"raw_orcid":"https://orcid.org/0000-0002-4386-1527","affiliations":[{"raw_affiliation_string":"Department of Software Engineering, Superior University, Lahore 54000, Pakistan","institution_ids":["https://openalex.org/I4210100043"]},{"raw_affiliation_string":"Faculty of Computer Science and Information Technology, Superior University, Lahore 54000, Pakistan","institution_ids":["https://openalex.org/I4210100043"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5037103657"],"corresponding_institution_ids":["https://openalex.org/I4210100043"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":5.8572,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.96691871,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"13","issue":"12","first_page":"315","last_page":"315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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":0.9987999796867371,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9987999796867371,"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":0.9958999752998352,"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/focus","display_name":"Focus (optics)","score":0.8137091398239136},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7947739362716675},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6693207025527954},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6455051898956299},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.605446457862854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4623594880104065},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4159781038761139}],"concepts":[{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.8137091398239136},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7947739362716675},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6693207025527954},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6455051898956299},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.605446457862854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4623594880104065},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4159781038761139},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/computers13120315","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers13120315","pdf_url":null,"source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},{"id":"pmh:oai:engagedscholarship.csuohio.edu:bus_facpub-1343","is_oa":true,"landing_page_url":"https://engagedscholarship.csuohio.edu/bus_facpub/355","pdf_url":null,"source":{"id":"https://openalex.org/S4306400889","display_name":"EngagedScholarship @ Cleveland State University (Cleveland State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102607778","host_organization_name":"Cleveland State University","host_organization_lineage":["https://openalex.org/I102607778"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Business Faculty Publications","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:2f31211793924cce8eaa8f6ddd8ddac1","is_oa":true,"landing_page_url":"https://doaj.org/article/2f31211793924cce8eaa8f6ddd8ddac1","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computers, Vol 13, Iss 12, p 315 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/computers13120315","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers13120315","pdf_url":null,"source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2036705578","https://openalex.org/W2095705004","https://openalex.org/W2123170466","https://openalex.org/W2499760652","https://openalex.org/W2531409750","https://openalex.org/W2941914178","https://openalex.org/W3012888109","https://openalex.org/W3019352575","https://openalex.org/W3022013598","https://openalex.org/W3032318421","https://openalex.org/W3038993799","https://openalex.org/W3081738998","https://openalex.org/W3092210029","https://openalex.org/W3095648847","https://openalex.org/W3109961563","https://openalex.org/W3120598210","https://openalex.org/W3130280533","https://openalex.org/W3150382221","https://openalex.org/W3155151741","https://openalex.org/W3158551918","https://openalex.org/W3166873558","https://openalex.org/W4206095984","https://openalex.org/W4206398892","https://openalex.org/W4212823851","https://openalex.org/W4221046698","https://openalex.org/W4289888496","https://openalex.org/W4295008916","https://openalex.org/W4296990078","https://openalex.org/W4310154196","https://openalex.org/W4318831690","https://openalex.org/W4319163914","https://openalex.org/W4391782441","https://openalex.org/W6674330103","https://openalex.org/W6842888371"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"Speech":[0],"emotion":[1],"recognition":[2],"(SER)":[3],"is":[4,20],"an":[5,172,178,199],"emerging":[6],"technology":[7],"that":[8,168],"utilizes":[9],"speech":[10],"sounds":[11],"to":[12,35,118,132,209],"identify":[13,36],"a":[14,44,78,126],"speaker\u2019s":[15],"emotional":[16,37],"state.":[17],"Computational":[18],"intelligence":[19],"receiving":[21],"increasing":[22],"attention":[23],"from":[24],"academics,":[25],"health,":[26],"and":[27,61,63,77,95,121,162,187,193],"social":[28],"media":[29],"applications.":[30],"This":[31],"research":[32],"was":[33],"conducted":[34],"states":[38],"in":[39],"verbal":[40],"communication.":[41],"We":[42,124],"applied":[43],"publicly":[45],"available":[46],"dataset":[47],"called":[48],"RAVDEES.":[49],"The":[50,166],"data":[51],"augmentation":[52],"process":[53],"involved":[54],"adding":[55],"noise,":[56],"applying":[57],"time":[58],"stretching,":[59],"shifting,":[60],"pitch,":[62],"extracting":[64],"the":[65,101,115,134],"features":[66],"zero":[67],"cross":[68],"rate":[69,142],"(ZCR),":[70],"chroma":[71],"shift,":[72],"Mel-Frequency":[73],"Cepstral":[74],"Coefficients":[75],"(MFCC),":[76],"spectrogram.":[79],"In":[80],"addition,":[81],"we":[82,110,169],"used":[83,125],"many":[84],"pretrained":[85],"deep":[86,102],"learning":[87,103],"models,":[88,104],"such":[89],"as":[90],"VGG16,":[91],"ResNet50,":[92],"Xception,":[93],"InceptionV3,":[94],"DenseNet121.":[96],"Out":[97],"of":[98,100,128,175,180,190,201],"all":[99],"Xception":[105,116],"yielded":[106],"superior":[107],"outcomes.":[108],"Furthermore,":[109],"improved":[111],"performance":[112,129],"by":[113],"changing":[114],"model":[117,167,205],"include":[119],"hyperparameters":[120],"additional":[122],"layers.":[123],"variety":[127],"evaluation":[130],"parameters":[131],"test":[133],"proposed":[135],"model.":[136],"These":[137],"included":[138],"F1-score,":[139],"accuracy,":[140],"misclassification":[141],"(MCR),":[143],"precision,":[144,185],"sensitivity,":[145,186],"specificity,":[146],"negative":[147,151],"predictive":[148],"value,":[149],"false":[150,153,156,159,163],"rate,":[152,155,158,161],"positive":[154],"discovery":[157,164],"omission":[160],"rate.":[165],"suggested":[170,204],"demonstrated":[171,206],"overall":[173],"accuracy":[174],"98%,":[176],"with":[177],"MCR":[179],"2%.":[181],"Additionally,":[182],"it":[183],"attained":[184,198],"specificity":[188],"values":[189],"91.99%,":[191],"91.78%,":[192],"98.68%,":[194],"respectively.":[195],"Additional":[196],"models":[197],"F1-score":[200],"91.83%.":[202],"Our":[203],"superiority":[207],"compared":[208],"other":[210],"cutting-edge":[211],"techniques":[212]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":11}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
